Merge branch 'stable/drivers' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/drivers' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/pciback: Have 'passthrough' option instead of XEN_PCIDEV_BACKEND_PASS and XEN_PCIDEV_BACKEND_VPCI
  xen/pciback: Remove the DEBUG option.
  xen/pciback: Drop two backends, squash and cleanup some code.
  xen/pciback: Print out the MSI/MSI-X (PIRQ) values
  xen/pciback: Don't setup an fake IRQ handler for SR-IOV devices.
  xen: rename pciback module to xen-pciback.
  xen/pciback: Fine-grain the spinlocks and fix BUG: scheduling while atomic cases.
  xen/pciback: Allocate IRQ handler for device that is shared with guest.
  xen/pciback: Disable MSI/MSI-X when reseting a device
  xen/pciback: guest SR-IOV support for PV guest
  xen/pciback: Register the owner (domain) of the PCI device.
  xen/pciback: Cleanup the driver based on checkpatch warnings and errors.
  xen/pciback: xen pci backend driver.
  xen: tmem: self-ballooning and frontswap-selfshrinking
  xen: Add module alias to autoload backend drivers
  xen: Populate xenbus device attributes
  xen: Add __attribute__((format(printf... where appropriate
  xen: prepare tmem shim to handle frontswap
  xen: allow enable use of VGA console on dom0

22 files changed, 5199 insertions, 51 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index a59638b37c1..03bc471c3ee 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -9,6 +9,23 @@ config XEN_BALLOON
 	  the system to expand the domain's memory allocation, or alternatively
 	  return unneeded memory to the system.
 
+config XEN_SELFBALLOONING
+	bool "Dynamically self-balloon kernel memory to target"
+	depends on XEN && XEN_BALLOON && CLEANCACHE && SWAP
+	default n
+	help
+	  Self-ballooning dynamically balloons available kernel memory driven
+	  by the current usage of anonymous memory ("committed AS") and
+	  controlled by various sysfs-settable parameters.  Configuring
+	  FRONTSWAP is highly recommended; if it is not configured, self-
+	  ballooning is disabled by default but can be enabled with the
+	  'selfballooning' kernel boot parameter.  If FRONTSWAP is configured,
+	  frontswap-selfshrinking is enabled by default but can be disabled
+	  with the 'noselfshrink' kernel boot parameter; and self-ballooning
+	  is enabled by default but can be disabled with the 'noselfballooning'
+	  kernel boot parameter.  Note that systems without a sufficiently
+	  large swap device should not enable self-ballooning.
+
 config XEN_SCRUB_PAGES
 	bool "Scrub pages before returning them to system"
 	depends on XEN_BALLOON
@@ -105,4 +122,33 @@ config SWIOTLB_XEN
 	depends on PCI
 	select SWIOTLB
 
+config XEN_TMEM
+	bool
+	default y if (CLEANCACHE || FRONTSWAP)
+	help
+	  Shim to interface in-kernel Transcendent Memory hooks
+	  (e.g. cleancache and frontswap) to Xen tmem hypercalls.
+
+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.
+
+	  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.
+
+	  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
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index bbc18258ecc..72bbb27d7a6 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,6 +1,5 @@
 obj-y	+= grant-table.o features.o events.o manage.o balloon.o
 obj-y	+= xenbus/
-obj-y	+= tmem.o
 
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_features.o			:= $(nostackp)
@@ -9,14 +8,17 @@ obj-$(CONFIG_BLOCK)			+= biomerge.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_XEN_XENCOMM)		+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)		+= xen-balloon.o
+obj-$(CONFIG_XEN_SELFBALLOONING)	+= xen-selfballoon.o
 obj-$(CONFIG_XEN_DEV_EVTCHN)		+= xen-evtchn.o
 obj-$(CONFIG_XEN_GNTDEV)		+= xen-gntdev.o
 obj-$(CONFIG_XEN_GRANT_DEV_ALLOC)	+= xen-gntalloc.o
 obj-$(CONFIG_XENFS)			+= xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 obj-$(CONFIG_XEN_PLATFORM_PCI)		+= xen-platform-pci.o
+obj-$(CONFIG_XEN_TMEM)			+= tmem.o
 obj-$(CONFIG_SWIOTLB_XEN)		+= swiotlb-xen.o
 obj-$(CONFIG_XEN_DOM0)			+= pci.o
+obj-$(CONFIG_XEN_PCIDEV_BACKEND)	+= xen-pciback/
 
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
index 816a44959ef..d369965e8f8 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -1,7 +1,7 @@
 /*
  * Xen implementation for transcendent memory (tmem)
  *
- * Copyright (C) 2009-2010 Oracle Corp.  All rights reserved.
+ * Copyright (C) 2009-2011 Oracle Corp.  All rights reserved.
  * Author: Dan Magenheimer
  */
 
@@ -9,8 +9,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
+#include <linux/module.h>
 #include <linux/cleancache.h>
 
+/* temporary ifdef until include/linux/frontswap.h is upstream */
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <asm/xen/hypercall.h>
@@ -122,14 +128,8 @@ static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid)
 	return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0);
 }
 
-static int xen_tmem_destroy_pool(u32 pool_id)
-{
-	struct tmem_oid oid = { { 0 } };
-
-	return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
-}
-
-int tmem_enabled;
+int tmem_enabled __read_mostly;
+EXPORT_SYMBOL(tmem_enabled);
 
 static int __init enable_tmem(char *s)
 {
@@ -139,6 +139,14 @@ static int __init enable_tmem(char *s)
 
 __setup("tmem", enable_tmem);
 
+#ifdef CONFIG_CLEANCACHE
+static int xen_tmem_destroy_pool(u32 pool_id)
+{
+	struct tmem_oid oid = { { 0 } };
+
+	return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
+}
+
 /* cleancache ops */
 
 static void tmem_cleancache_put_page(int pool, struct cleancache_filekey key,
@@ -240,18 +248,156 @@ static struct cleancache_ops tmem_cleancache_ops = {
 	.init_shared_fs = tmem_cleancache_init_shared_fs,
 	.init_fs = tmem_cleancache_init_fs
 };
+#endif
 
-static int __init xen_tmem_init(void)
+#ifdef CONFIG_FRONTSWAP
+/* frontswap tmem operations */
+
+/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+static int tmem_frontswap_poolid;
+
+/*
+ * Swizzling increases objects per swaptype, increasing tmem concurrency
+ * for heavy swaploads.  Later, larger nr_cpus -> larger SWIZ_BITS
+ */
+#define SWIZ_BITS		4
+#define SWIZ_MASK		((1 << SWIZ_BITS) - 1)
+#define _oswiz(_type, _ind)	((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
+#define iswiz(_ind)		(_ind >> SWIZ_BITS)
+
+static inline struct tmem_oid oswiz(unsigned type, u32 ind)
 {
-	struct cleancache_ops old_ops;
+	struct tmem_oid oid = { .oid = { 0 } };
+	oid.oid[0] = _oswiz(type, ind);
+	return oid;
+}
 
+/* returns 0 if the page was successfully put into frontswap, -1 if not */
+static int tmem_frontswap_put_page(unsigned type, pgoff_t offset,
+				   struct page *page)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	unsigned long pfn = page_to_pfn(page);
+	int pool = tmem_frontswap_poolid;
+	int ret;
+
+	if (pool < 0)
+		return -1;
+	if (ind64 != ind)
+		return -1;
+	mb(); /* ensure page is quiescent; tmem may address it with an alias */
+	ret = xen_tmem_put_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+	/* translate Xen tmem return values to linux semantics */
+	if (ret == 1)
+		return 0;
+	else
+		return -1;
+}
+
+/*
+ * returns 0 if the page was successfully gotten from frontswap, -1 if
+ * was not present (should never happen!)
+ */
+static int tmem_frontswap_get_page(unsigned type, pgoff_t offset,
+				   struct page *page)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	unsigned long pfn = page_to_pfn(page);
+	int pool = tmem_frontswap_poolid;
+	int ret;
+
+	if (pool < 0)
+		return -1;
+	if (ind64 != ind)
+		return -1;
+	ret = xen_tmem_get_page(pool, oswiz(type, ind), iswiz(ind), pfn);
+	/* translate Xen tmem return values to linux semantics */
+	if (ret == 1)
+		return 0;
+	else
+		return -1;
+}
+
+/* flush a single page from frontswap */
+static void tmem_frontswap_flush_page(unsigned type, pgoff_t offset)
+{
+	u64 ind64 = (u64)offset;
+	u32 ind = (u32)offset;
+	int pool = tmem_frontswap_poolid;
+
+	if (pool < 0)
+		return;
+	if (ind64 != ind)
+		return;
+	(void) xen_tmem_flush_page(pool, oswiz(type, ind), iswiz(ind));
+}
+
+/* flush all pages from the passed swaptype */
+static void tmem_frontswap_flush_area(unsigned type)
+{
+	int pool = tmem_frontswap_poolid;
+	int ind;
+
+	if (pool < 0)
+		return;
+	for (ind = SWIZ_MASK; ind >= 0; ind--)
+		(void)xen_tmem_flush_object(pool, oswiz(type, ind));
+}
+
+static void tmem_frontswap_init(unsigned ignored)
+{
+	struct tmem_pool_uuid private = TMEM_POOL_PRIVATE_UUID;
+
+	/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
+	if (tmem_frontswap_poolid < 0)
+		tmem_frontswap_poolid =
+		    xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE);
+}
+
+static int __initdata use_frontswap = 1;
+
+static int __init no_frontswap(char *s)
+{
+	use_frontswap = 0;
+	return 1;
+}
+
+__setup("nofrontswap", no_frontswap);
+
+static struct frontswap_ops tmem_frontswap_ops = {
+	.put_page = tmem_frontswap_put_page,
+	.get_page = tmem_frontswap_get_page,
+	.flush_page = tmem_frontswap_flush_page,
+	.flush_area = tmem_frontswap_flush_area,
+	.init = tmem_frontswap_init
+};
+#endif
+
+static int __init xen_tmem_init(void)
+{
 	if (!xen_domain())
 		return 0;
+#ifdef CONFIG_FRONTSWAP
+	if (tmem_enabled && use_frontswap) {
+		char *s = "";
+		struct frontswap_ops old_ops =
+			frontswap_register_ops(&tmem_frontswap_ops);
+
+		tmem_frontswap_poolid = -1;
+		if (old_ops.init != NULL)
+			s = " (WARNING: frontswap_ops overridden)";
+		printk(KERN_INFO "frontswap enabled, RAM provided by "
+				 "Xen Transcendent Memory\n");
+	}
+#endif
 #ifdef CONFIG_CLEANCACHE
 	BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
 	if (tmem_enabled && use_cleancache) {
 		char *s = "";
-		old_ops = cleancache_register_ops(&tmem_cleancache_ops);
+		struct cleancache_ops old_ops =
+			cleancache_register_ops(&tmem_cleancache_ops);
 		if (old_ops.init_fs != NULL)
 			s = " (WARNING: cleancache_ops overridden)";
 		printk(KERN_INFO "cleancache enabled, RAM provided by "
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index a4ff225ee86..5c9dc43c1e9 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -98,6 +98,8 @@ static int __init balloon_init(void)
 
 	register_balloon(&balloon_sysdev);
 
+	register_xen_selfballooning(&balloon_sysdev);
+
 	target_watch.callback = watch_target;
 	xenstore_notifier.notifier_call = balloon_init_watcher;
 
diff --git a/drivers/xen/xen-pciback/Makefile b/drivers/xen/xen-pciback/Makefile
new file mode 100644
index 00000000000..ffe0ad3438b
--- /dev/null
+++ b/drivers/xen/xen-pciback/Makefile
@@ -0,0 +1,7 @@
+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 vpci.o \
+		 passthrough.o
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
new file mode 100644
index 00000000000..a8031445d94
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -0,0 +1,438 @@
+/*
+ * PCI Backend - Functions for creating a virtual configuration space for
+ *               exported PCI Devices.
+ *               It's dangerous to allow PCI Driver Domains to change their
+ *               device's resources (memory, i/o ports, interrupts). We need to
+ *               restrict changes to certain PCI Configuration registers:
+ *               BARs, INTERRUPT_PIN, most registers in the header...
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+#include "conf_space_quirks.h"
+
+#define DRV_NAME	"xen-pciback"
+static int permissive;
+module_param(permissive, bool, 0644);
+
+/* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word,
+ * xen_pcibk_write_config_word, and xen_pcibk_write_config_byte are created. */
+#define DEFINE_PCI_CONFIG(op, size, type)			\
+int xen_pcibk_##op##_config_##size				\
+(struct pci_dev *dev, int offset, type value, void *data)	\
+{								\
+	return pci_##op##_config_##size(dev, offset, value);	\
+}
+
+DEFINE_PCI_CONFIG(read, byte, u8 *)
+DEFINE_PCI_CONFIG(read, word, u16 *)
+DEFINE_PCI_CONFIG(read, dword, u32 *)
+
+DEFINE_PCI_CONFIG(write, byte, u8)
+DEFINE_PCI_CONFIG(write, word, u16)
+DEFINE_PCI_CONFIG(write, dword, u32)
+
+static int conf_space_read(struct pci_dev *dev,
+			   const struct config_field_entry *entry,
+			   int offset, u32 *value)
+{
+	int ret = 0;
+	const struct config_field *field = entry->field;
+
+	*value = 0;
+
+	switch (field->size) {
+	case 1:
+		if (field->u.b.read)
+			ret = field->u.b.read(dev, offset, (u8 *) value,
+					      entry->data);
+		break;
+	case 2:
+		if (field->u.w.read)
+			ret = field->u.w.read(dev, offset, (u16 *) value,
+					      entry->data);
+		break;
+	case 4:
+		if (field->u.dw.read)
+			ret = field->u.dw.read(dev, offset, value, entry->data);
+		break;
+	}
+	return ret;
+}
+
+static int conf_space_write(struct pci_dev *dev,
+			    const struct config_field_entry *entry,
+			    int offset, u32 value)
+{
+	int ret = 0;
+	const struct config_field *field = entry->field;
+
+	switch (field->size) {
+	case 1:
+		if (field->u.b.write)
+			ret = field->u.b.write(dev, offset, (u8) value,
+					       entry->data);
+		break;
+	case 2:
+		if (field->u.w.write)
+			ret = field->u.w.write(dev, offset, (u16) value,
+					       entry->data);
+		break;
+	case 4:
+		if (field->u.dw.write)
+			ret = field->u.dw.write(dev, offset, value,
+						entry->data);
+		break;
+	}
+	return ret;
+}
+
+static inline u32 get_mask(int size)
+{
+	if (size == 1)
+		return 0xff;
+	else if (size == 2)
+		return 0xffff;
+	else
+		return 0xffffffff;
+}
+
+static inline int valid_request(int offset, int size)
+{
+	/* Validate request (no un-aligned requests) */
+	if ((size == 1 || size == 2 || size == 4) && (offset % size) == 0)
+		return 1;
+	return 0;
+}
+
+static inline u32 merge_value(u32 val, u32 new_val, u32 new_val_mask,
+			      int offset)
+{
+	if (offset >= 0) {
+		new_val_mask <<= (offset * 8);
+		new_val <<= (offset * 8);
+	} else {
+		new_val_mask >>= (offset * -8);
+		new_val >>= (offset * -8);
+	}
+	val = (val & ~new_val_mask) | (new_val & new_val_mask);
+
+	return val;
+}
+
+static int pcibios_err_to_errno(int err)
+{
+	switch (err) {
+	case PCIBIOS_SUCCESSFUL:
+		return XEN_PCI_ERR_success;
+	case PCIBIOS_DEVICE_NOT_FOUND:
+		return XEN_PCI_ERR_dev_not_found;
+	case PCIBIOS_BAD_REGISTER_NUMBER:
+		return XEN_PCI_ERR_invalid_offset;
+	case PCIBIOS_FUNC_NOT_SUPPORTED:
+		return XEN_PCI_ERR_not_implemented;
+	case PCIBIOS_SET_FAILED:
+		return XEN_PCI_ERR_access_denied;
+	}
+	return err;
+}
+
+int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
+			  u32 *ret_val)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+	int req_start, req_end, field_start, field_end;
+	/* if read fails for any reason, return 0
+	 * (as if device didn't respond) */
+	u32 value = 0, tmp_val;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: read %d bytes at 0x%x\n",
+		       pci_name(dev), size, offset);
+
+	if (!valid_request(offset, size)) {
+		err = XEN_PCI_ERR_invalid_offset;
+		goto out;
+	}
+
+	/* Get the real value first, then modify as appropriate */
+	switch (size) {
+	case 1:
+		err = pci_read_config_byte(dev, offset, (u8 *) &value);
+		break;
+	case 2:
+		err = pci_read_config_word(dev, offset, (u16 *) &value);
+		break;
+	case 4:
+		err = pci_read_config_dword(dev, offset, &value);
+		break;
+	}
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		req_start = offset;
+		req_end = offset + size;
+		field_start = OFFSET(cfg_entry);
+		field_end = OFFSET(cfg_entry) + field->size;
+
+		if ((req_start >= field_start && req_start < field_end)
+		    || (req_end > field_start && req_end <= field_end)) {
+			err = conf_space_read(dev, cfg_entry, field_start,
+					      &tmp_val);
+			if (err)
+				goto out;
+
+			value = merge_value(value, tmp_val,
+					    get_mask(field->size),
+					    field_start - req_start);
+		}
+	}
+
+out:
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: read %d bytes at 0x%x = %x\n",
+		       pci_name(dev), size, offset, value);
+
+	*ret_val = value;
+	return pcibios_err_to_errno(err);
+}
+
+int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
+{
+	int err = 0, handled = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+	u32 tmp_val;
+	int req_start, req_end, field_start, field_end;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG
+		       DRV_NAME ": %s: write request %d bytes at 0x%x = %x\n",
+		       pci_name(dev), size, offset, value);
+
+	if (!valid_request(offset, size))
+		return XEN_PCI_ERR_invalid_offset;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		req_start = offset;
+		req_end = offset + size;
+		field_start = OFFSET(cfg_entry);
+		field_end = OFFSET(cfg_entry) + field->size;
+
+		if ((req_start >= field_start && req_start < field_end)
+		    || (req_end > field_start && req_end <= field_end)) {
+			tmp_val = 0;
+
+			err = xen_pcibk_config_read(dev, field_start,
+						  field->size, &tmp_val);
+			if (err)
+				break;
+
+			tmp_val = merge_value(tmp_val, value, get_mask(size),
+					      req_start - field_start);
+
+			err = conf_space_write(dev, cfg_entry, field_start,
+					       tmp_val);
+
+			/* handled is set true here, but not every byte
+			 * may have been written! Properly detecting if
+			 * every byte is handled is unnecessary as the
+			 * flag is used to detect devices that need
+			 * special helpers to work correctly.
+			 */
+			handled = 1;
+		}
+	}
+
+	if (!handled && !err) {
+		/* By default, anything not specificially handled above is
+		 * read-only. The permissive flag changes this behavior so
+		 * that anything not specifically handled above is writable.
+		 * This means that some fields may still be read-only because
+		 * they have entries in the config_field list that intercept
+		 * the write and do nothing. */
+		if (dev_data->permissive || permissive) {
+			switch (size) {
+			case 1:
+				err = pci_write_config_byte(dev, offset,
+							    (u8) value);
+				break;
+			case 2:
+				err = pci_write_config_word(dev, offset,
+							    (u16) value);
+				break;
+			case 4:
+				err = pci_write_config_dword(dev, offset,
+							     (u32) value);
+				break;
+			}
+		} else if (!dev_data->warned_on_write) {
+			dev_data->warned_on_write = 1;
+			dev_warn(&dev->dev, "Driver tried to write to a "
+				 "read-only configuration space field at offset"
+				 " 0x%x, size %d. This may be harmless, but if "
+				 "you have problems with your device:\n"
+				 "1) see permissive attribute in sysfs\n"
+				 "2) report problems to the xen-devel "
+				 "mailing list along with details of your "
+				 "device obtained from lspci.\n", offset, size);
+		}
+	}
+
+	return pcibios_err_to_errno(err);
+}
+
+void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry, *t;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "free-ing dynamically allocated virtual "
+			   "configuration space fields\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry_safe(cfg_entry, t, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		if (field->clean) {
+			field->clean((struct config_field *)field);
+
+			kfree(cfg_entry->data);
+
+			list_del(&cfg_entry->list);
+			kfree(cfg_entry);
+		}
+
+	}
+}
+
+void xen_pcibk_config_reset_dev(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	const struct config_field_entry *cfg_entry;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "resetting virtual configuration space\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		field = cfg_entry->field;
+
+		if (field->reset)
+			field->reset(dev, OFFSET(cfg_entry), cfg_entry->data);
+	}
+}
+
+void xen_pcibk_config_free_dev(struct pci_dev *dev)
+{
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry, *t;
+	const struct config_field *field;
+
+	dev_dbg(&dev->dev, "free-ing virtual configuration space fields\n");
+	if (!dev_data)
+		return;
+
+	list_for_each_entry_safe(cfg_entry, t, &dev_data->config_fields, list) {
+		list_del(&cfg_entry->list);
+
+		field = cfg_entry->field;
+
+		if (field->release)
+			field->release(dev, OFFSET(cfg_entry), cfg_entry->data);
+
+		kfree(cfg_entry);
+	}
+}
+
+int xen_pcibk_config_add_field_offset(struct pci_dev *dev,
+				    const struct config_field *field,
+				    unsigned int base_offset)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry;
+	void *tmp;
+
+	cfg_entry = kmalloc(sizeof(*cfg_entry), GFP_KERNEL);
+	if (!cfg_entry) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	cfg_entry->data = NULL;
+	cfg_entry->field = field;
+	cfg_entry->base_offset = base_offset;
+
+	/* silently ignore duplicate fields */
+	err = xen_pcibk_field_is_dup(dev, OFFSET(cfg_entry));
+	if (err)
+		goto out;
+
+	if (field->init) {
+		tmp = field->init(dev, OFFSET(cfg_entry));
+
+		if (IS_ERR(tmp)) {
+			err = PTR_ERR(tmp);
+			goto out;
+		}
+
+		cfg_entry->data = tmp;
+	}
+
+	dev_dbg(&dev->dev, "added config field at offset 0x%02x\n",
+		OFFSET(cfg_entry));
+	list_add_tail(&cfg_entry->list, &dev_data->config_fields);
+
+out:
+	if (err)
+		kfree(cfg_entry);
+
+	return err;
+}
+
+/* This sets up the device's virtual configuration space to keep track of
+ * certain registers (like the base address registers (BARs) so that we can
+ * keep the client from manipulating them directly.
+ */
+int xen_pcibk_config_init_dev(struct pci_dev *dev)
+{
+	int err = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+
+	dev_dbg(&dev->dev, "initializing virtual configuration space\n");
+
+	INIT_LIST_HEAD(&dev_data->config_fields);
+
+	err = xen_pcibk_config_header_add_fields(dev);
+	if (err)
+		goto out;
+
+	err = xen_pcibk_config_capability_add_fields(dev);
+	if (err)
+		goto out;
+
+	err = xen_pcibk_config_quirks_init(dev);
+
+out:
+	return err;
+}
+
+int xen_pcibk_config_init(void)
+{
+	return xen_pcibk_config_capability_init();
+}
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
new file mode 100644
index 00000000000..e56c934ad13
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -0,0 +1,126 @@
+/*
+ * PCI Backend - Common data structures for overriding the configuration space
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#ifndef __XEN_PCIBACK_CONF_SPACE_H__
+#define __XEN_PCIBACK_CONF_SPACE_H__
+
+#include <linux/list.h>
+#include <linux/err.h>
+
+/* conf_field_init can return an errno in a ptr with ERR_PTR() */
+typedef void *(*conf_field_init) (struct pci_dev *dev, int offset);
+typedef void (*conf_field_reset) (struct pci_dev *dev, int offset, void *data);
+typedef void (*conf_field_free) (struct pci_dev *dev, int offset, void *data);
+
+typedef int (*conf_dword_write) (struct pci_dev *dev, int offset, u32 value,
+				 void *data);
+typedef int (*conf_word_write) (struct pci_dev *dev, int offset, u16 value,
+				void *data);
+typedef int (*conf_byte_write) (struct pci_dev *dev, int offset, u8 value,
+				void *data);
+typedef int (*conf_dword_read) (struct pci_dev *dev, int offset, u32 *value,
+				void *data);
+typedef int (*conf_word_read) (struct pci_dev *dev, int offset, u16 *value,
+			       void *data);
+typedef int (*conf_byte_read) (struct pci_dev *dev, int offset, u8 *value,
+			       void *data);
+
+/* These are the fields within the configuration space which we
+ * are interested in intercepting reads/writes to and changing their
+ * values.
+ */
+struct config_field {
+	unsigned int offset;
+	unsigned int size;
+	unsigned int mask;
+	conf_field_init init;
+	conf_field_reset reset;
+	conf_field_free release;
+	void (*clean) (struct config_field *field);
+	union {
+		struct {
+			conf_dword_write write;
+			conf_dword_read read;
+		} dw;
+		struct {
+			conf_word_write write;
+			conf_word_read read;
+		} w;
+		struct {
+			conf_byte_write write;
+			conf_byte_read read;
+		} b;
+	} u;
+	struct list_head list;
+};
+
+struct config_field_entry {
+	struct list_head list;
+	const struct config_field *field;
+	unsigned int base_offset;
+	void *data;
+};
+
+#define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
+
+/* Add fields to a device - the add_fields macro expects to get a pointer to
+ * the first entry in an array (of which the ending is marked by size==0)
+ */
+int xen_pcibk_config_add_field_offset(struct pci_dev *dev,
+				    const struct config_field *field,
+				    unsigned int offset);
+
+static inline int xen_pcibk_config_add_field(struct pci_dev *dev,
+					   const struct config_field *field)
+{
+	return xen_pcibk_config_add_field_offset(dev, field, 0);
+}
+
+static inline int xen_pcibk_config_add_fields(struct pci_dev *dev,
+					    const struct config_field *field)
+{
+	int i, err = 0;
+	for (i = 0; field[i].size != 0; i++) {
+		err = xen_pcibk_config_add_field(dev, &field[i]);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static inline int xen_pcibk_config_add_fields_offset(struct pci_dev *dev,
+					const struct config_field *field,
+					unsigned int offset)
+{
+	int i, err = 0;
+	for (i = 0; field[i].size != 0; i++) {
+		err = xen_pcibk_config_add_field_offset(dev, &field[i], offset);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+/* Read/Write the real configuration space */
+int xen_pcibk_read_config_byte(struct pci_dev *dev, int offset, u8 *value,
+			       void *data);
+int xen_pcibk_read_config_word(struct pci_dev *dev, int offset, u16 *value,
+			       void *data);
+int xen_pcibk_read_config_dword(struct pci_dev *dev, int offset, u32 *value,
+				void *data);
+int xen_pcibk_write_config_byte(struct pci_dev *dev, int offset, u8 value,
+				 void *data);
+int xen_pcibk_write_config_word(struct pci_dev *dev, int offset, u16 value,
+				void *data);
+int xen_pcibk_write_config_dword(struct pci_dev *dev, int offset, u32 value,
+				 void *data);
+
+int xen_pcibk_config_capability_init(void);
+
+int xen_pcibk_config_header_add_fields(struct pci_dev *dev);
+int xen_pcibk_config_capability_add_fields(struct pci_dev *dev);
+
+#endif				/* __XEN_PCIBACK_CONF_SPACE_H__ */
diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c
new file mode 100644
index 00000000000..7f83e9083e9
--- /dev/null
+++ b/drivers/xen/xen-pciback/conf_space_capab