2 files changed, 201 insertions, 135 deletions

diff --git a/lib/librte_eal/linuxapp/igb_uio/compat.h b/lib/librte_eal/linuxapp/igb_uio/compat.h
index b800a53c..ce456d4b 100644
--- a/lib/librte_eal/linuxapp/igb_uio/compat.h
+++ b/lib/librte_eal/linuxapp/igb_uio/compat.h
@@ -16,12 +16,9 @@
 #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
+#define PCI_MSIX_ENTRY_SIZE            16
+#define PCI_MSIX_ENTRY_VECTOR_CTRL     12
+#define PCI_MSIX_ENTRY_CTRL_MASKBIT    1
 #endif
 
 /*
@@ -124,6 +121,14 @@ static bool pci_check_and_mask_intx(struct pci_dev *pdev)
 
 #endif /* < 3.3.0 */
 
-#if LINUX_VERSION_CODE < KERNEL_VERSION(4, 8, 0)
-#define HAVE_PCI_ENABLE_MSIX
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 8, 0)
+#define HAVE_ALLOC_IRQ_VECTORS 1
+#endif
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 3, 0)
+#define HAVE_MSI_LIST_IN_GENERIC_DEVICE 1
+#endif
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 5, 0)
+#define HAVE_PCI_MSI_MASK_IRQ 1
 #endif
diff --git a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
index 07a19a31..a3a98c17 100644
--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
+++ b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
@@ -29,13 +29,11 @@
 #include <linux/pci.h>
 #include <linux/uio_driver.h>
 #include <linux/io.h>
+#include <linux/irq.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"
@@ -51,7 +49,6 @@ struct rte_uio_pci_dev {
 
 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,
@@ -91,14 +88,16 @@ static struct attribute *dev_attrs[] = {
 static const struct attribute_group dev_attr_grp = {
 	.attrs = dev_attrs,
 };
+
+#ifndef HAVE_PCI_MSI_MASK_IRQ
 /*
  * It masks the msix on/off of generating MSI-X messages.
  */
 static void
-igbuio_msix_mask_irq(struct msi_desc *desc, int32_t state)
+igbuio_msix_mask_irq(struct msi_desc *desc, s32 state)
 {
 	u32 mask_bits = desc->masked;
-	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+	unsigned int offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
 						PCI_MSIX_ENTRY_VECTOR_CTRL;
 
 	if (state != 0)
@@ -113,6 +112,52 @@ igbuio_msix_mask_irq(struct msi_desc *desc, int32_t state)
 	}
 }
 
+/*
+ * It masks the msi on/off of generating MSI messages.
+ */
+static void
+igbuio_msi_mask_irq(struct pci_dev *pdev, struct msi_desc *desc, int32_t state)
+{
+	u32 mask_bits = desc->masked;
+	u32 offset = desc->irq - pdev->irq;
+	u32 mask = 1 << offset;
+
+	if (!desc->msi_attrib.maskbit)
+		return;
+
+	if (state != 0)
+		mask_bits &= ~mask;
+	else
+		mask_bits |= mask;
+
+	if (mask_bits != desc->masked) {
+		pci_write_config_dword(pdev, desc->mask_pos, mask_bits);
+		desc->masked = mask_bits;
+	}
+}
+
+static void
+igbuio_mask_irq(struct pci_dev *pdev, enum rte_intr_mode mode, s32 irq_state)
+{
+	struct msi_desc *desc;
+	struct list_head *msi_list;
+
+#ifdef HAVE_MSI_LIST_IN_GENERIC_DEVICE
+	msi_list = &pdev->dev.msi_list;
+#else
+	msi_list = &pdev->msi_list;
+#endif
+
+	if (mode == RTE_INTR_MODE_MSIX) {
+		list_for_each_entry(desc, msi_list, list)
+			igbuio_msix_mask_irq(desc, irq_state);
+	} else if (mode == RTE_INTR_MODE_MSI) {
+		list_for_each_entry(desc, msi_list, list)
+			igbuio_msi_mask_irq(pdev, desc, irq_state);
+	}
+}
+#endif
+
 /**
  * This is the irqcontrol callback to be registered to uio_info.
  * It can be used to disable/enable interrupt from user space processes.
@@ -132,21 +177,26 @@ 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);
+#ifdef HAVE_PCI_MSI_MASK_IRQ
+	struct irq_data *irq = irq_get_irq_data(udev->info.irq);
+#endif
 
-	else if (udev->mode == RTE_INTR_MODE_MSIX) {
-		struct msi_desc *desc;
+	pci_cfg_access_lock(pdev);
 
-#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);
+	if (udev->mode == RTE_INTR_MODE_MSIX || udev->mode == RTE_INTR_MODE_MSI) {
+#ifdef HAVE_PCI_MSI_MASK_IRQ
+		if (irq_state == 1)
+			pci_msi_unmask_irq(irq);
+		else
+			pci_msi_mask_irq(irq);
 #else
-		list_for_each_entry(desc, &pdev->dev.msi_list, list)
-			igbuio_msix_mask_irq(desc, irq_state);
+		igbuio_mask_irq(pdev, udev->mode, irq_state);
 #endif
 	}
+
+	if (udev->mode == RTE_INTR_MODE_LEGACY)
+		pci_intx(pdev, !!irq_state);
+
 	pci_cfg_access_unlock(pdev);
 
 	return 0;
@@ -157,19 +207,125 @@ igbuio_pci_irqcontrol(struct uio_info *info, s32 irq_state)
  * If yes, disable it here and will be enable later.
  */
 static irqreturn_t
-igbuio_pci_irqhandler(int irq, struct uio_info *info)
+igbuio_pci_irqhandler(int irq, void *dev_id)
 {
-	struct rte_uio_pci_dev *udev = info->priv;
+	struct rte_uio_pci_dev *udev = (struct rte_uio_pci_dev *)dev_id;
+	struct uio_info *info = &udev->info;
 
 	/* Legacy mode need to mask in hardware */
 	if (udev->mode == RTE_INTR_MODE_LEGACY &&
 	    !pci_check_and_mask_intx(udev->pdev))
 		return IRQ_NONE;
 
+	uio_event_notify(info);
+
 	/* Message signal mode, no share IRQ and automasked */
 	return IRQ_HANDLED;
 }
 
+static int
+igbuio_pci_enable_interrupts(struct rte_uio_pci_dev *udev)
+{
+	int err = 0;
+#ifndef HAVE_ALLOC_IRQ_VECTORS
+	struct msix_entry msix_entry;
+#endif
+
+	switch (igbuio_intr_mode_preferred) {
+	case RTE_INTR_MODE_MSIX:
+		/* Only 1 msi-x vector needed */
+#ifndef HAVE_ALLOC_IRQ_VECTORS
+		msix_entry.entry = 0;
+		if (pci_enable_msix(udev->pdev, &msix_entry, 1) == 0) {
+			dev_dbg(&udev->pdev->dev, "using MSI-X");
+			udev->info.irq_flags = IRQF_NO_THREAD;
+			udev->info.irq = msix_entry.vector;
+			udev->mode = RTE_INTR_MODE_MSIX;
+			break;
+		}
+#else
+		if (pci_alloc_irq_vectors(udev->pdev, 1, 1, PCI_IRQ_MSIX) == 1) {
+			dev_dbg(&udev->pdev->dev, "using MSI-X");
+			udev->info.irq_flags = IRQF_NO_THREAD;
+			udev->info.irq = pci_irq_vector(udev->pdev, 0);
+			udev->mode = RTE_INTR_MODE_MSIX;
+			break;
+		}
+#endif
+
+	/* fall back to MSI */
+	case RTE_INTR_MODE_MSI:
+#ifndef HAVE_ALLOC_IRQ_VECTORS
+		if (pci_enable_msi(udev->pdev) == 0) {
+			dev_dbg(&udev->pdev->dev, "using MSI");
+			udev->info.irq_flags = IRQF_NO_THREAD;
+			udev->info.irq = udev->pdev->irq;
+			udev->mode = RTE_INTR_MODE_MSI;
+			break;
+		}
+#else
+		if (pci_alloc_irq_vectors(udev->pdev, 1, 1, PCI_IRQ_MSI) == 1) {
+			dev_dbg(&udev->pdev->dev, "using MSI");
+			udev->info.irq_flags = IRQF_NO_THREAD;
+			udev->info.irq = pci_irq_vector(udev->pdev, 0);
+			udev->mode = RTE_INTR_MODE_MSI;
+			break;
+		}
+#endif
+	/* fall back to INTX */
+	case RTE_INTR_MODE_LEGACY:
+		if (pci_intx_mask_supported(udev->pdev)) {
+			dev_dbg(&udev->pdev->dev, "using INTX");
+			udev->info.irq_flags = IRQF_SHARED | IRQF_NO_THREAD;
+			udev->info.irq = udev->pdev->irq;
+			udev->mode = RTE_INTR_MODE_LEGACY;
+			break;
+		}
+		dev_notice(&udev->pdev->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 = UIO_IRQ_NONE;
+		break;
+
+	default:
+		dev_err(&udev->pdev->dev, "invalid IRQ mode %u",
+			igbuio_intr_mode_preferred);
+		udev->info.irq = UIO_IRQ_NONE;
+		err = -EINVAL;
+	}
+
+	if (udev->info.irq != UIO_IRQ_NONE)
+		err = request_irq(udev->info.irq, igbuio_pci_irqhandler,
+				  udev->info.irq_flags, udev->info.name,
+				  udev);
+	dev_info(&udev->pdev->dev, "uio device registered with irq %lx\n",
+		 udev->info.irq);
+
+	return err;
+}
+
+static void
+igbuio_pci_disable_interrupts(struct rte_uio_pci_dev *udev)
+{
+	if (udev->info.irq) {
+		free_irq(udev->info.irq, udev);
+		udev->info.irq = 0;
+	}
+
+#ifndef HAVE_ALLOC_IRQ_VECTORS
+	if (udev->mode == RTE_INTR_MODE_MSIX)
+		pci_disable_msix(udev->pdev);
+	if (udev->mode == RTE_INTR_MODE_MSI)
+		pci_disable_msi(udev->pdev);
+#else
+	if (udev->mode == RTE_INTR_MODE_MSIX ||
+	    udev->mode == RTE_INTR_MODE_MSI)
+		pci_free_irq_vectors(udev->pdev);
+#endif
+}
+
+
 /**
  * This gets called while opening uio device file.
  */
@@ -178,12 +334,17 @@ igbuio_pci_open(struct uio_info *info, struct inode *inode)
 {
 	struct rte_uio_pci_dev *udev = info->priv;
 	struct pci_dev *dev = udev->pdev;
-
-	pci_reset_function(dev);
+	int err;
 
 	/* set bus master, which was cleared by the reset function */
 	pci_set_master(dev);
 
+	/* enable interrupts */
+	err = igbuio_pci_enable_interrupts(udev);
+	if (err) {
+		dev_err(&dev->dev, "Enable interrupt fails\n");
+		return err;
+	}
 	return 0;
 }
 
@@ -193,60 +354,15 @@ igbuio_pci_release(struct uio_info *info, struct inode *inode)
 	struct rte_uio_pci_dev *udev = info->priv;
 	struct pci_dev *dev = udev->pdev;
 
+	/* disable interrupts */
+	igbuio_pci_disable_interrupts(udev);
+
 	/* stop the device from further DMA */
 	pci_clear_master(dev);
 
-	pci_reset_function(dev);
-
 	return 0;
 }
 
-#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,
@@ -356,9 +472,6 @@ static int
 igbuio_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	struct rte_uio_pci_dev *udev;
-#ifdef HAVE_PCI_ENABLE_MSIX
-	struct msix_entry msix_entry;
-#endif
 	dma_addr_t map_dma_addr;
 	void *map_addr;
 	int err;
@@ -401,61 +514,12 @@ igbuio_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* 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;
 	udev->info.open = igbuio_pci_open;
 	udev->info.release = igbuio_pci_release;
-#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 */
-#ifdef HAVE_PCI_ENABLE_MSIX
-		msix_entry.entry = 0;
-		if (pci_enable_msix(dev, &msix_entry, 1) == 0) {
-			dev_dbg(&dev->dev, "using MSI-X");
-			udev->info.irq_flags = IRQF_NO_THREAD;
-			udev->info.irq = msix_entry.vector;
-			udev->mode = RTE_INTR_MODE_MSIX;
-			break;
-		}
-#else
-		if (pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_MSIX) == 1) {
-			dev_dbg(&dev->dev, "using MSI-X");
-			udev->info.irq = pci_irq_vector(dev, 0);
-			udev->mode = RTE_INTR_MODE_MSIX;
-			break;
-		}
-#endif
-		/* 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 | IRQF_NO_THREAD;
-			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;
@@ -467,9 +531,6 @@ igbuio_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	pci_set_drvdata(dev, udev);
 
-	dev_info(&dev->dev, "uio device registered with irq %lx\n",
-		 udev->info.irq);
-
 	/*
 	 * Doing a harmless dma mapping for attaching the device to
 	 * the iommu identity mapping if kernel boots with iommu=pt.
@@ -497,8 +558,6 @@ 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_disable_device(dev);
 fail_free:
 	kfree(udev);
@@ -514,8 +573,6 @@ igbuio_pci_remove(struct pci_dev *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_disable_device(dev);
 	pci_set_drvdata(dev, NULL);
 	kfree(udev);
@@ -532,6 +589,9 @@ igbuio_config_intr_mode(char *intr_str)
 	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_MSI_NAME)) {
+		igbuio_intr_mode_preferred = RTE_INTR_MODE_MSI;
+		pr_info("Use MSI 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");
@@ -575,6 +635,7 @@ 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_MSI_NAME "        Use MSI interrupt\n"
 "    " RTE_INTR_MODE_LEGACY_NAME "     Use Legacy interrupt\n"
 "\n");