xen/pciback: Have 'passthrough' option instead of XEN_PCIDEV_BACKEND_PASS and...

xen/pciback: Have 'passthrough' option instead of XEN_PCIDEV_BACKEND_PASS and XEN_PCIDEV_BACKEND_VPCI

.. compile options. This way the user can decide during runtime whether they
want the default 'vpci' (virtual pci passthrough) or where the PCI devices
are passed in without any BDF renumbering. The option 'passthrough' allows
the user to toggle the it from 0 (vpci) to 1 (passthrough).
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

drivers/xen/Kconfig

@@ -109,34 +109,22 @@ config XEN_PCIDEV_BACKEND
 	tristate "Xen PCI-device backend driver"
 	depends on PCI && X86 && XEN
 	depends on XEN_BACKEND
+	default m
 	help
 	  The PCI device backend driver allows the kernel to export arbitrary
 	  PCI devices to other guests. If you select this to be a module, you
 	  will need to make sure no other driver has bound to the device(s)
 	  you want to make visible to other guests.
 
-choice
-	prompt "PCI Backend Mode"
-	depends on XEN_PCIDEV_BACKEND
-
-config XEN_PCIDEV_BACKEND_VPCI
-	bool "Virtual PCI"
-	help
-	  This PCI Backend hides the true PCI topology and makes the frontend
-	  think there is a single PCI bus with only the exported devices on it.
-	  For example, a device at 03:05.0 will be re-assigned to 00:00.0. A
-	  second device at 02:1a.1 will be re-assigned to 00:01.1.
-
-config XEN_PCIDEV_BACKEND_PASS
-	bool "Passthrough"
-	help
-	  This PCI Backend provides a real view of the PCI topology to the
-	  frontend (for example, a device at 06:01.b will still appear at
-	  06:01.b to the frontend). This is similar to how Xen 2.0.x exposed
-	  PCI devices to its driver domains. This may be required for drivers
-	  which depend on finding their hardward in certain bus/slot
-	  locations.
+	  The parameter "passthrough" allows you specify how you want the PCI
+	  devices to appear in the guest. You can choose the default (0) where
+	  PCI topology starts at 00.00.0, or (1) for passthrough if you want
+	  the PCI devices topology appear the same as in the host.
 
-endchoice
+	  The "hide" parameter (only applicable if backend driver is compiled
+	  into the kernel) allows you to bind the PCI devices to this module
+	  from the default device drivers. The argument is the list of PCI BDFs:
+	  xen-pciback.hide=(03:00.0)(04:00.0)
 
+	  If in doubt, say m.
 endmenu

drivers/xen/xen-pciback/Makefile

@@ -3,6 +3,5 @@ obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback.o
 xen-pciback-y := pci_stub.o pciback_ops.o xenbus.o
 xen-pciback-y += conf_space.o conf_space_header.o \
 		 conf_space_capability.o \
-		 conf_space_quirks.o
-xen-pciback-$(CONFIG_XEN_PCIDEV_BACKEND_VPCI) += vpci.o
-xen-pciback-$(CONFIG_XEN_PCIDEV_BACKEND_PASS) += passthrough.o
+		 conf_space_quirks.o vpci.o \
+		 passthrough.o

drivers/xen/xen-pciback/passthrough.c

@@ -16,9 +16,10 @@ struct passthrough_dev_data {
 	spinlock_t lock;
 };
 
-struct pci_dev *xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
-				      unsigned int domain, unsigned int bus,
-				      unsigned int devfn)
+static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_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;
@@ -41,8 +42,9 @@ struct pci_dev *xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
 	return dev;
 }
 
-int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev,
-			  int devid, publish_pci_dev_cb publish_cb)
+static int __xen_pcibk_add_pci_dev(struct xen_pcibk_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;
@@ -68,8 +70,8 @@ int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev,
 	return err;
 }
 
-void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-			       struct pci_dev *dev)
+static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev)
 {
 	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
 	struct pci_dev_entry *dev_entry, *t;
@@ -92,7 +94,7 @@ void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 		pcistub_put_pci_dev(found_dev);
 }
 
-int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
 {
 	struct passthrough_dev_data *dev_data;
 
@@ -109,8 +111,8 @@ int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
 	return 0;
 }
 
-int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
-				publish_pci_root_cb publish_root_cb)
+static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					 publish_pci_root_cb publish_root_cb)
 {
 	int err = 0;
 	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
@@ -154,7 +156,7 @@ int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
 	return err;
 }
 
-void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 {
 	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
 	struct pci_dev_entry *dev_entry, *t;
@@ -169,13 +171,24 @@ void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 	pdev->pci_dev_data = NULL;
 }
 
-int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
-			       struct xen_pcibk_device *pdev,
-			       unsigned int *domain, unsigned int *bus,
-			       unsigned int *devfn)
+static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					struct xen_pcibk_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;
 }
+
+struct xen_pcibk_backend xen_pcibk_passthrough_backend = {
+	.name           = "passthrough",
+	.init           = __xen_pcibk_init_devices,
+	.free		= __xen_pcibk_release_devices,
+	.find           = __xen_pcibk_get_pcifront_dev,
+	.publish        = __xen_pcibk_publish_pci_roots,
+	.release        = __xen_pcibk_release_pci_dev,
+	.add            = __xen_pcibk_add_pci_dev,
+	.get            = __xen_pcibk_get_pci_dev,
+};

drivers/xen/xen-pciback/pciback.h

@@ -83,30 +83,90 @@ typedef int (*publish_pci_dev_cb) (struct xen_pcibk_device *pdev,
 				   unsigned int devfn, unsigned int devid);
 typedef int (*publish_pci_root_cb) (struct xen_pcibk_device *pdev,
 				    unsigned int domain, unsigned int bus);
-int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev,
-			  int devid, publish_pci_dev_cb publish_cb);
-void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-			       struct pci_dev *dev);
-struct pci_dev *xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
-				      unsigned int domain, unsigned int bus,
-				      unsigned int devfn);
 
+/* Backend registration for the two types of BDF representation:
+ *  vpci - BDFs start at 00
+ *  passthrough - BDFs are exactly like in the host.
+ */
+struct xen_pcibk_backend {
+	char *name;
+	int (*init)(struct xen_pcibk_device *pdev);
+	void (*free)(struct xen_pcibk_device *pdev);
+	int (*find)(struct pci_dev *pcidev, struct xen_pcibk_device *pdev,
+		    unsigned int *domain, unsigned int *bus,
+		    unsigned int *devfn);
+	int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb);
+	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev);
+	int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
+		   int devid, publish_pci_dev_cb publish_cb);
+	struct pci_dev *(*get)(struct xen_pcibk_device *pdev,
+			       unsigned int domain, unsigned int bus,
+			       unsigned int devfn);
+};
+
+extern struct xen_pcibk_backend xen_pcibk_vpci_backend;
+extern struct xen_pcibk_backend xen_pcibk_passthrough_backend;
+extern struct xen_pcibk_backend *xen_pcibk_backend;
+
+static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev,
+					int devid,
+					publish_pci_dev_cb publish_cb)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->add)
+		return xen_pcibk_backend->add(pdev, dev, devid, publish_cb);
+	return -1;
+};
+static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					     struct pci_dev *dev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->free)
+		return xen_pcibk_backend->release(pdev, dev);
+};
+
+static inline struct pci_dev *
+xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, unsigned int domain,
+		      unsigned int bus, unsigned int devfn)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->get)
+		return xen_pcibk_backend->get(pdev, domain, bus, devfn);
+	return NULL;
+};
 /**
 * Add for domain0 PCIE-AER handling. Get guest domain/bus/devfn in xen_pcibk
 * before sending aer request to pcifront, so that guest could identify
 * device, coopearte with xen_pcibk to finish aer recovery job if device driver
 * has the capability
 */
-
-int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
-			       struct xen_pcibk_device *pdev,
-			       unsigned int *domain, unsigned int *bus,
-			       unsigned int *devfn);
-int xen_pcibk_init_devices(struct xen_pcibk_device *pdev);
-int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
-				publish_pci_root_cb cb);
-void xen_pcibk_release_devices(struct xen_pcibk_device *pdev);
-
+static inline int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					     struct xen_pcibk_device *pdev,
+					     unsigned int *domain,
+					     unsigned int *bus,
+					     unsigned int *devfn)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->find)
+		return xen_pcibk_backend->find(pcidev, pdev, domain, bus,
+					       devfn);
+	return -1;
+};
+static inline int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->init)
+		return xen_pcibk_backend->init(pdev);
+	return -1;
+};
+static inline int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					      publish_pci_root_cb cb)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->publish)
+		return xen_pcibk_backend->publish(pdev, cb);
+	return -1;
+};
+static inline void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+{
+	if (xen_pcibk_backend && xen_pcibk_backend->free)
+		return xen_pcibk_backend->free(pdev);
+};
 /* Handles events from front-end */
 irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id);
 void xen_pcibk_do_op(struct work_struct *data);

drivers/xen/xen-pciback/vpci.c

@@ -25,9 +25,10 @@ static inline struct list_head *list_first(struct list_head *head)
 	return head->next;
 }
 
-struct pci_dev *xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
-				      unsigned int domain, unsigned int bus,
-				      unsigned int devfn)
+static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev,
+					       unsigned int domain,
+					       unsigned int bus,
+					       unsigned int devfn)
 {
 	struct pci_dev_entry *entry;
 	struct pci_dev *dev = NULL;
@@ -63,8 +64,9 @@ static inline int match_slot(struct pci_dev *l, struct pci_dev *r)
 	return 0;
 }
 
-int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev,
-			  int devid, publish_pci_dev_cb publish_cb)
+static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
+				   struct pci_dev *dev, int devid,
+				   publish_pci_dev_cb publish_cb)
 {
 	int err = 0, slot, func = -1;
 	struct pci_dev_entry *t, *dev_entry;
@@ -137,8 +139,8 @@ int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev,
 	return err;
 }
 
-void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-			       struct pci_dev *dev)
+static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
+					struct pci_dev *dev)
 {
 	int slot;
 	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
@@ -167,7 +169,7 @@ void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 		pcistub_put_pci_dev(found_dev);
 }
 
-int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
 {
 	int slot;
 	struct vpci_dev_data *vpci_dev;
@@ -186,14 +188,14 @@ int xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
 	return 0;
 }
 
-int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
-				publish_pci_root_cb publish_cb)
+static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev,
+					 publish_pci_root_cb publish_cb)
 {
 	/* The Virtual PCI bus has only one root */
 	return publish_cb(pdev, 0, 0);
 }
 
-void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 {
 	int slot;
 	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
@@ -212,10 +214,10 @@ void xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 	pdev->pci_dev_data = NULL;
 }
 
-int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
-			       struct xen_pcibk_device *pdev,
-			       unsigned int *domain, unsigned int *bus,
-			       unsigned int *devfn)
+static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
+					struct xen_pcibk_device *pdev,
+					unsigned int *domain, unsigned int *bus,
+					unsigned int *devfn)
 {
 	struct pci_dev_entry *entry;
 	struct pci_dev *dev = NULL;
@@ -244,3 +246,14 @@ int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev,
 	spin_unlock_irqrestore(&vpci_dev->lock, flags);
 	return found;
 }
+
+struct xen_pcibk_backend xen_pcibk_vpci_backend = {
+	.name		= "vpci",
+	.init		= __xen_pcibk_init_devices,
+	.free		= __xen_pcibk_release_devices,
+	.find		= __xen_pcibk_get_pcifront_dev,
+	.publish	= __xen_pcibk_publish_pci_roots,
+	.release	= __xen_pcibk_release_pci_dev,
+	.add		= __xen_pcibk_add_pci_dev,
+	.get		= __xen_pcibk_get_pci_dev,
+};

drivers/xen/xen-pciback/xenbus.c

@@ -18,6 +18,21 @@
 #define INVALID_EVTCHN_IRQ  (-1)
 struct workqueue_struct *xen_pcibk_wq;
 
+static int __read_mostly passthrough;
+module_param(passthrough, bool, S_IRUGO);
+MODULE_PARM_DESC(passthrough,
+	"Option to specify how to export PCI topology to guest:\n"\
+	" 0 - (default) Hide the true PCI topology and makes the frontend\n"\
+	"   there is a single PCI bus with only the exported devices on it.\n"\
+	"   For example, a device at 03:05.0 will be re-assigned to 00:00.0\n"\
+	"   while second device at 02:1a.1 will be re-assigned to 00:01.1.\n"\
+	" 1 - Passthrough provides a real view of the PCI topology to the\n"\
+	"   frontend (for example, a device at 06:01.b will still appear at\n"\
+	"   06:01.b to the frontend). This is similar to how Xen 2.0.x\n"\
+	"   exposed PCI devices to its driver domains. This may be required\n"\
+	"   for drivers which depend on finding their hardward in certain\n"\
+	"   bus/slot locations.");
+
 static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev)
 {
 	struct xen_pcibk_device *pdev;
@@ -710,6 +725,8 @@ static struct xenbus_driver xenbus_xen_pcibk_driver = {
 	.otherend_changed	= xen_pcibk_frontend_changed,
 };
 
+struct xen_pcibk_backend *xen_pcibk_backend;
+
 int __init xen_pcibk_xenbus_register(void)
 {
 	xen_pcibk_wq = create_workqueue("xen_pciback_workqueue");
@@ -718,6 +735,10 @@ int __init xen_pcibk_xenbus_register(void)
 			"xen_pciback_workqueue failed\n", __func__);
 		return -EFAULT;
 	}
+	xen_pcibk_backend = &xen_pcibk_vpci_backend;
+	if (passthrough)
+		xen_pcibk_backend = &xen_pcibk_passthrough_backend;
+	pr_info(DRV_NAME ": backend is %s\n", xen_pcibk_backend->name);
 	return xenbus_register_backend(&xenbus_xen_pcibk_driver);
 }