xen/pciback: xen pci backend driver.

This is the host side counterpart to the frontend driver in
drivers/pci/xen-pcifront.c. The PV protocol is also implemented by
frontend drivers in other OSes too, such as the BSDs.

The PV protocol is rather simple. There is page shared with the guest,
which has the 'struct xen_pci_sharedinfo' embossed in it. The backend
has a thread that is kicked every-time the structure is changed and
based on the operation field it performs specific tasks:

 XEN_PCI_OP_conf_[read|write]:
   Read/Write 0xCF8/0xCFC filtered data. (conf_space*.c)
   Based on which field is probed, we either enable/disable the PCI
   device, change power state, read VPD, etc. The major goal of this
   call is to provide a Physical IRQ (PIRQ) to the guest.

   The PIRQ is Xen hypervisor global IRQ value irrespective of the IRQ
   is tied in to the IO-APIC, or is a vector. For GSI type
   interrupts, the PIRQ==GSI holds. For MSI/MSI-X the
   PIRQ value != Linux IRQ number (thought PIRQ==vector).

   Please note, that with Xen, all interrupts (except those level shared ones)
   are injected directly to the guest - there is no host interaction.

 XEN_PCI_OP_[enable|disable]_msi[|x] (pciback_ops.c)
   Enables/disables the MSI/MSI-X capability of the device. These operations
   setup the MSI/MSI-X vectors for the guest and pass them to the frontend.

   When the device is activated, the interrupts are directly injected in the
   guest without involving the host.

 XEN_PCI_OP_aer_[detected|resume|mmio|slotreset]: In case of failure,
  perform the appropriate AER commands on the guest. Right now that is
  a cop-out - we just kill the guest.

Besides implementing those commands, it can also

 - hide a PCI device from the host. When booting up, the user can specify
   xen-pciback.hide=(1:0:0)(BDF..) so that host does not try to use the
   device.

The driver was lifted from linux-2.6.18.hg tree and fixed up
so that it could compile under v3.0. Per suggestion from Jesse Barnes
moved the driver to drivers/xen/xen-pciback.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

1 files changed, 178 insertions, 0 deletions

diff --git a/drivers/xen/xen-pciback/passthrough.c b/drivers/xen/xen-pciback/passthrough.c
new file mode 100644
index 0000000..5386bebf
--- /dev/null
+++ b/drivers/xen/xen-pciback/passthrough.c
@@ -0,0 +1,178 @@
+/*
+ * PCI Backend - Provides restricted access to the real PCI bus topology
+ *               to the frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include "pciback.h"
+
+struct passthrough_dev_data {
+	/* Access to dev_list must be protected by lock */
+	struct list_head dev_list;
+	spinlock_t lock;
+};
+
+struct pci_dev *pciback_get_pci_dev(struct pciback_device *pdev,
+				    unsigned int domain, unsigned int bus,
+				    unsigned int devfn)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry;
+	struct pci_dev *dev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_data->lock, flags);
+
+	list_for_each_entry(dev_entry, &dev_data->dev_list, list) {
+		if (domain == (unsigned int)pci_domain_nr(dev_entry->dev->bus)
+		    && bus == (unsigned int)dev_entry->dev->bus->number
+		    && devfn == dev_entry->dev->devfn) {
+			dev = dev_entry->dev;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&dev_data->lock, flags);
+
+	return dev;
+}
+
+int pciback_add_pci_dev(struct pciback_device *pdev, struct pci_dev *dev,
+			int devid, publish_pci_dev_cb publish_cb)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry;
+	unsigned long flags;
+	unsigned int domain, bus, devfn;
+	int err;
+
+	dev_entry = kmalloc(sizeof(*dev_entry), GFP_KERNEL);
+	if (!dev_entry)
+		return -ENOMEM;
+	dev_entry->dev = dev;
+
+	spin_lock_irqsave(&dev_data->lock, flags);
+	list_add_tail(&dev_entry->list, &dev_data->dev_list);
+	spin_unlock_irqrestore(&dev_data->lock, flags);
+
+	/* Publish this device. */
+	domain = (unsigned int)pci_domain_nr(dev->bus);
+	bus = (unsigned int)dev->bus->number;
+	devfn = dev->devfn;
+	err = publish_cb(pdev, domain, bus, devfn, devid);
+
+	return err;
+}
+
+void pciback_release_pci_dev(struct pciback_device *pdev, struct pci_dev *dev)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *t;
+	struct pci_dev *found_dev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_data->lock, flags);
+
+	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		if (dev_entry->dev == dev) {
+			list_del(&dev_entry->list);
+			found_dev = dev_entry->dev;
+			kfree(dev_entry);
+		}
+	}
+
+	spin_unlock_irqrestore(&dev_data->lock, flags);
+
+	if (found_dev)
+		pcistub_put_pci_dev(found_dev);
+}
+
+int pciback_init_devices(struct pciback_device *pdev)
+{
+	struct passthrough_dev_data *dev_data;
+
+	dev_data = kmalloc(sizeof(*dev_data), GFP_KERNEL);
+	if (!dev_data)
+		return -ENOMEM;
+
+	spin_lock_init(&dev_data->lock);
+
+	INIT_LIST_HEAD(&dev_data->dev_list);
+
+	pdev->pci_dev_data = dev_data;
+
+	return 0;
+}
+
+int pciback_publish_pci_roots(struct pciback_device *pdev,
+			      publish_pci_root_cb publish_root_cb)
+{
+	int err = 0;
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *e;
+	struct pci_dev *dev;
+	int found;
+	unsigned int domain, bus;
+
+	spin_lock(&dev_data->lock);
+
+	list_for_each_entry(dev_entry, &dev_data->dev_list, list) {
+		/* Only publish this device as a root if none of its
+		 * parent bridges are exported
+		 */
+		found = 0;
+		dev = dev_entry->dev->bus->self;
+		for (; !found && dev != NULL; dev = dev->bus->self) {
+			list_for_each_entry(e, &dev_data->dev_list, list) {
+				if (dev == e->dev) {
+					found = 1;
+					break;
+				}
+			}
+		}
+
+		domain = (unsigned int)pci_domain_nr(dev_entry->dev->bus);
+		bus = (unsigned int)dev_entry->dev->bus->number;
+
+		if (!found) {
+			err = publish_root_cb(pdev, domain, bus);
+			if (err)
+				break;
+		}
+	}
+
+	spin_unlock(&dev_data->lock);
+
+	return err;
+}
+
+void pciback_release_devices(struct pciback_device *pdev)
+{
+	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
+	struct pci_dev_entry *dev_entry, *t;
+
+	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		list_del(&dev_entry->list);
+		pcistub_put_pci_dev(dev_entry->dev);
+		kfree(dev_entry);
+	}
+
+	kfree(dev_data);
+	pdev->pci_dev_data = NULL;
+}
+
+int pciback_get_pcifront_dev(struct pci_dev *pcidev,
+			     struct pciback_device *pdev,
+			     unsigned int *domain, unsigned int *bus,
+			     unsigned int *devfn)
+
+{
+	*domain = pci_domain_nr(pcidev->bus);
+	*bus = pcidev->bus->number;
+	*devfn = pcidev->devfn;
+	return 1;
+}