#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>
-#ifdef RTE_PCI_CONFIG
-#define PCI_SYS_FILE_BUF_SIZE 10
-#define PCI_DEV_CAP_REG 0xA4
-#define PCI_DEV_CTRL_REG 0xA8
-#define PCI_DEV_CAP_EXT_TAG_MASK 0x20
-#define PCI_DEV_CTRL_EXT_TAG_SHIFT 8
-#define PCI_DEV_CTRL_EXT_TAG_MASK (1 << PCI_DEV_CTRL_EXT_TAG_SHIFT)
-#endif
+#include "compat.h"
/**
* A structure describing the private information for a uio device.
enum rte_intr_mode mode;
};
-static char *intr_mode = NULL;
+static char *intr_mode;
static enum rte_intr_mode igbuio_intr_mode_preferred = RTE_INTR_MODE_MSIX;
-static inline struct rte_uio_pci_dev *
-igbuio_get_uio_pci_dev(struct uio_info *info)
-{
- return container_of(info, struct rte_uio_pci_dev, info);
-}
-
/* sriov sysfs */
-#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
-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
-
static ssize_t
show_max_vfs(struct device *dev, struct device_attribute *attr,
char *buf)
{
- return snprintf(buf, 10, "%u\n",
- pci_num_vf(container_of(dev, struct pci_dev, dev)));
+ return snprintf(buf, 10, "%u\n", dev_num_vf(dev));
}
static ssize_t
{
int err = 0;
unsigned long max_vfs;
- struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+ struct pci_dev *pdev = to_pci_dev(dev);
- if (0 != strict_strtoul(buf, 0, &max_vfs))
+ if (0 != kstrtoul(buf, 0, &max_vfs))
return -EINVAL;
if (0 == max_vfs)
return err ? err : count;
}
-#ifdef RTE_PCI_CONFIG
-static ssize_t
-show_extended_tag(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct pci_dev *pci_dev = container_of(dev, struct pci_dev, dev);
- uint32_t val = 0;
-
- pci_read_config_dword(pci_dev, PCI_DEV_CAP_REG, &val);
- if (!(val & PCI_DEV_CAP_EXT_TAG_MASK)) /* Not supported */
- return snprintf(buf, PCI_SYS_FILE_BUF_SIZE, "%s\n", "invalid");
-
- val = 0;
- pci_bus_read_config_dword(pci_dev->bus, pci_dev->devfn,
- PCI_DEV_CTRL_REG, &val);
-
- return snprintf(buf, PCI_SYS_FILE_BUF_SIZE, "%s\n",
- (val & PCI_DEV_CTRL_EXT_TAG_MASK) ? "on" : "off");
-}
-
-static ssize_t
-store_extended_tag(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct pci_dev *pci_dev = container_of(dev, struct pci_dev, dev);
- uint32_t val = 0, enable;
-
- if (strncmp(buf, "on", 2) == 0)
- enable = 1;
- else if (strncmp(buf, "off", 3) == 0)
- enable = 0;
- else
- return -EINVAL;
-
- pci_cfg_access_lock(pci_dev);
- pci_bus_read_config_dword(pci_dev->bus, pci_dev->devfn,
- PCI_DEV_CAP_REG, &val);
- if (!(val & PCI_DEV_CAP_EXT_TAG_MASK)) { /* Not supported */
- pci_cfg_access_unlock(pci_dev);
- return -EPERM;
- }
-
- val = 0;
- pci_bus_read_config_dword(pci_dev->bus, pci_dev->devfn,
- PCI_DEV_CTRL_REG, &val);
- if (enable)
- val |= PCI_DEV_CTRL_EXT_TAG_MASK;
- else
- val &= ~PCI_DEV_CTRL_EXT_TAG_MASK;
- pci_bus_write_config_dword(pci_dev->bus, pci_dev->devfn,
- PCI_DEV_CTRL_REG, val);
- pci_cfg_access_unlock(pci_dev);
-
- return count;
-}
-
-static ssize_t
-show_max_read_request_size(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct pci_dev *pci_dev = container_of(dev, struct pci_dev, dev);
- int val = pcie_get_readrq(pci_dev);
-
- return snprintf(buf, PCI_SYS_FILE_BUF_SIZE, "%d\n", val);
-}
-
-static ssize_t
-store_max_read_request_size(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct pci_dev *pci_dev = container_of(dev, struct pci_dev, dev);
- unsigned long size = 0;
- int ret;
-
- if (strict_strtoul(buf, 0, &size) != 0)
- return -EINVAL;
-
- ret = pcie_set_readrq(pci_dev, (int)size);
- if (ret < 0)
- return ret;
-
- return count;
-}
-#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,
};
.attrs = dev_attrs,
};
-#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
-/* 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
-
-/*
- * 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;
- }
-}
-
-static void
-igbuio_msi_mask_irq(struct irq_data *data, u32 enable)
-{
- struct msi_desc *desc = irq_data_get_msi(data);
- u32 mask_bits = desc->masked;
- unsigned offset = data->irq - desc->dev->irq;
- u32 mask = 1 << offset;
- u32 flag = enable << offset;
-
- mask_bits &= ~mask;
- mask_bits |= flag;
-
- if (desc->msi_attrib.maskbit && mask_bits != desc->masked) {
- pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);
- 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.
static int
igbuio_pci_irqcontrol(struct uio_info *info, s32 irq_state)
{
- struct rte_uio_pci_dev *udev = igbuio_get_uio_pci_dev(info);
+ struct rte_uio_pci_dev *udev = info->priv;
struct pci_dev *pdev = udev->pdev;
+#ifdef HAVE_IRQ_DATA
+ struct irq_data *irq = irq_get_irq_data(udev->info.irq);
+#else
+ unsigned int irq = udev->info.irq;
+#endif
+
pci_cfg_access_lock(pdev);
+
+ 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
+ if (irq_state == 1)
+ unmask_msi_irq(irq);
+ else
+ mask_msi_irq(irq);
+#endif
+ }
+
if (udev->mode == RTE_INTR_MODE_LEGACY)
pci_intx(pdev, !!irq_state);
- else if (udev->mode == RTE_INTR_MODE_MSI) {
- struct irq_data *data = irq_get_irq_data(pdev->irq);
- igbuio_msi_mask_irq(data, !!irq_state);
- } else if (udev->mode == RTE_INTR_MODE_MSIX) {
- struct msi_desc *desc;
-
- list_for_each_entry(desc, &pdev->msi_list, list)
- igbuio_msix_mask_irq(desc, irq_state);
- }
pci_cfg_access_unlock(pdev);
return 0;
static irqreturn_t
igbuio_pci_irqhandler(int irq, struct uio_info *info)
{
- struct rte_uio_pci_dev *udev = igbuio_get_uio_pci_dev(info);
+ struct rte_uio_pci_dev *udev = info->priv;
/* Legacy mode need to mask in hardware */
if (udev->mode == RTE_INTR_MODE_LEGACY &&
return IRQ_HANDLED;
}
+/**
+ * This gets called while opening uio device file.
+ */
+static int
+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);
+
+ /* set bus master, which was cleared by the reset function */
+ pci_set_master(dev);
+
+ return 0;
+}
+
+static int
+igbuio_pci_release(struct uio_info *info, struct inode *inode)
+{
+ struct rte_uio_pci_dev *udev = info->priv;
+ struct pci_dev *dev = udev->pdev;
+
+ /* 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)
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,
unsigned long addr, len;
void *internal_addr;
- if (sizeof(info->mem) / sizeof(info->mem[0]) <= n)
+ if (n >= ARRAY_SIZE(info->mem))
return -EINVAL;
addr = pci_resource_start(dev, pci_bar);
{
unsigned long addr, len;
- if (sizeof(info->port) / sizeof(info->port[0]) <= n)
+ if (n >= ARRAY_SIZE(info->port))
return -EINVAL;
addr = pci_resource_start(dev, pci_bar);
}
}
+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);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+static void
+igbuio_pci_disable_interrupts(struct rte_uio_pci_dev *udev)
+{
+#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
+}
+
static int
igbuio_setup_bars(struct pci_dev *dev, struct uio_info *info)
{
iom = 0;
iop = 0;
- for (i = 0; i != sizeof(bar_names) / sizeof(bar_names[0]); i++) {
+ 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);
}
}
- return (iom != 0) ? ret : -ENOENT;
+ return (iom != 0 || iop != 0) ? ret : -ENOENT;
}
#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 8, 0)
igbuio_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
struct rte_uio_pci_dev *udev;
- struct msix_entry msix_entry;
+ dma_addr_t map_dma_addr;
+ void *map_addr;
int err;
udev = kzalloc(sizeof(struct rte_uio_pci_dev), GFP_KERNEL);
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);
udev->info.version = "0.1";
udev->info.handler = igbuio_pci_irqhandler;
udev->info.irqcontrol = igbuio_pci_irqcontrol;
- udev->info.irq = dev->irq;
+ 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.priv = udev;
udev->pdev = dev;
- switch (igbuio_intr_mode_preferred) {
- case RTE_INTR_MODE_NONE:
- udev->info.irq = 0;
- break;
- 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 MSI */
- case RTE_INTR_MODE_MSI:
- if (pci_enable_msi(dev) == 0) {
- dev_dbg(&dev->dev, "using MSI");
- udev->mode = RTE_INTR_MODE_MSI;
- 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->mode = RTE_INTR_MODE_LEGACY;
- } else {
- dev_err(&dev->dev, "PCI INTX mask not supported\n");
- err = -EIO;
- goto fail_release_iomem;
- }
- break;
- default:
- dev_err(&dev->dev, "invalid IRQ mode %u",
- igbuio_intr_mode_preferred);
- err = -EINVAL;
+ err = igbuio_pci_enable_interrupts(udev);
+ if (err != 0)
goto fail_release_iomem;
- }
err = sysfs_create_group(&dev->dev.kobj, &dev_attr_grp);
if (err != 0)
- goto fail_release_iomem;
+ goto fail_disable_interrupts;
/* register uio driver */
err = uio_register_device(&dev->dev, &udev->info);
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.
+ * Note this is not a problem if no IOMMU at all.
+ */
+ map_addr = dma_alloc_coherent(&dev->dev, 1024, &map_dma_addr,
+ GFP_KERNEL);
+ if (map_addr)
+ memset(map_addr, 0, 1024);
+
+ if (!map_addr)
+ dev_info(&dev->dev, "dma mapping failed\n");
+ else {
+ dev_info(&dev->dev, "mapping 1K dma=%#llx host=%p\n",
+ (unsigned long long)map_dma_addr, map_addr);
+
+ dma_free_coherent(&dev->dev, 1024, map_addr, map_dma_addr);
+ dev_info(&dev->dev, "unmapping 1K dma=%#llx host=%p\n",
+ (unsigned long long)map_dma_addr, map_addr);
+ }
+
return 0;
fail_remove_group:
sysfs_remove_group(&dev->dev.kobj, &dev_attr_grp);
+fail_disable_interrupts:
+ igbuio_pci_disable_interrupts(udev);
fail_release_iomem:
igbuio_pci_release_iomem(&udev->info);
- if (udev->mode == RTE_INTR_MODE_MSIX)
- pci_disable_msix(udev->pdev);
- else if (udev->mode == RTE_INTR_MODE_MSI)
- pci_disable_msi(udev->pdev);
- pci_release_regions(dev);
-fail_disable:
pci_disable_device(dev);
fail_free:
kfree(udev);
static void
igbuio_pci_remove(struct pci_dev *dev)
{
- struct uio_info *info = pci_get_drvdata(dev);
- struct rte_uio_pci_dev *udev = igbuio_get_uio_pci_dev(info);
-
- if (info->priv == NULL) {
- pr_notice("Not igbuio device\n");
- return;
- }
+ struct rte_uio_pci_dev *udev = pci_get_drvdata(dev);
sysfs_remove_group(&dev->dev.kobj, &dev_attr_grp);
- uio_unregister_device(info);
- igbuio_pci_release_iomem(info);
- if (udev->mode == RTE_INTR_MODE_MSIX)
- pci_disable_msix(dev);
- else if (udev->mode == RTE_INTR_MODE_MSI)
- pci_disable_msi(dev);
- pci_release_regions(dev);
+ uio_unregister_device(&udev->info);
+ igbuio_pci_disable_interrupts(udev);
+ igbuio_pci_release_iomem(&udev->info);
pci_disable_device(dev);
pci_set_drvdata(dev, NULL);
- kfree(info);
+ kfree(udev);
}
static int