pci_disable_msi Oops Bug - linux-device-driver

Question

I am trying to write a kernel module that will handle MSI interrupts for a PCIe device. I have written a simple skeleton outline for my driver currently and whenever I try to call 'pci_disable_msi(dev)' I get an unable to handle kernel NULL pointer dereference error. I am following along exactly as described from the /Documentation/PCI/MSI-HOWTO.txt and it seems to me that I should not be getting this error. Is this a bug or is my setup incorrect? Judging by the last print that occures, I am pretty sure that it is happening at the fpga_remove() when I call pci_disable_msi(). (Clearly this occures when I am removing the module)
static struct pci_driver fpga_driver = {
.name = "PCIe_test",
.id_table = fpga_dev_table,
.probe = fpga_probe,
.remove = fpga_remove,
.suspend = fpga_suspend,
.resume = fpga_resume,
};
static irqreturn_t fpga_isr(int irq, struct pci_dev *dev)
{
printk(KERN_NOTICE "THIS is the ISR\n");
return IRQ_HANDLED;
}
static int setup_MSI_interrupt(struct pci_dev *dev, int num_msi)
{
int result;
result = pci_enable_msi(dev);
if(result)
{
printk(KERN_WARNING "Could not enable MSI\n");
return result;
}
printk(KERN_NOTICE "MSI has been enabled\n");
printk(KERN_NOTICE "dev->irq line is %d", dev->irq);
result = request_irq(dev->irq, fpga_isr, IRQF_SHARED, fpga_driver.name, dev);
printk(KERN_NOTICE "Using IRQ num %d\n", dev->irq);
if (result) {
dev_err(&dev->dev, "Failed to allocate irq %d: %d\n", dev->irq, result);
goto exit1;
}
dev_info(&dev->dev, "FPGA using PCIe Interrupt\n");
return 0;
exit1:
return -1;
}
static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
printk(KERN_NOTICE "Probing driver\n");
switch(dev->vendor) {
case VENDOR://0x1708:
printk(KERN_NOTICE "Xilinx device found\n");
break;
default:
printk(KERN_NOTICE "Device found that does not match id: id = 0x%04X\n", dev->device);
};
int err = pci_enable_device(dev);
if (err) {
dev_err(&dev->dev, "Failed to enable FPGA PCI device (%d)\n", err);
goto exit;
}
err = setup_MSI_interrupt(dev, NUM_MSI);
if(err)
goto exit;
return 0;
exit:
return -1;
}
static void fpga_remove(struct pci_dev *dev)
{
printk(KERN_NOTICE "REMOVING IRQ # %d\n", dev->irq);
free_irq(dev->irq, dev);
printk(KERN_NOTICE "IRQ has been freed\n");
pci_disable_msi(dev); // This causes a NUll Pointer to be dereferenced but needs to be added
printk(KERN_NOTICE "MSI has been disabled\n");
}
static int __init fpga_init(void)
{
printk(KERN_NOTICE "Registering Driver\n");
return pci_register_driver(&fpga_driver);
return 0;
}

Answer 1

You should probably not use the struct pci_dev as void *dev_id parameter in the request_irq(...) and the free_irq(...) functions. Its important to call them with the right and the same unique dev_id parameter for the interrupt. Doing this not could cause the kernel panic at pci_disable_msi() on removing the module.
Read more here:
What is dev_id parameter in request_irq?