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

arch/x86/xen/Makefile

@@ -18,5 +18,5 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o

arch/x86/xen/enlighten.c

@@ -1248,6 +1248,14 @@ asmlinkage void __init xen_start_kernel(void)
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
+		const struct dom0_vga_console_info *info =
+			(void *)((char *)xen_start_info +
+				 xen_start_info->console.dom0.info_off);
+
+		xen_init_vga(info, xen_start_info->console.dom0.info_size);
+		xen_start_info->console.domU.mfn = 0;
+		xen_start_info->console.domU.evtchn = 0;
+
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}

arch/x86/xen/vga.c

@@ -0,0 +1,67 @@
+#include <linux/screen_info.h>
+#include <linux/init.h>
+
+#include <asm/bootparam.h>
+#include <asm/setup.h>
+
+#include <xen/interface/xen.h>
+
+#include "xen-ops.h"
+
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+{
+	struct screen_info *screen_info = &boot_params.screen_info;
+
+	/* This is drawn from a dump from vgacon:startup in
+	 * standard Linux. */
+	screen_info->orig_video_mode = 3;
+	screen_info->orig_video_isVGA = 1;
+	screen_info->orig_video_lines = 25;
+	screen_info->orig_video_cols = 80;
+	screen_info->orig_video_ega_bx = 3;
+	screen_info->orig_video_points = 16;
+	screen_info->orig_y = screen_info->orig_video_lines - 1;
+
+	switch (info->video_type) {
+	case XEN_VGATYPE_TEXT_MODE_3:
+		if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3)
+		    + sizeof(info->u.text_mode_3))
+			break;
+		screen_info->orig_video_lines = info->u.text_mode_3.rows;
+		screen_info->orig_video_cols = info->u.text_mode_3.columns;
+		screen_info->orig_x = info->u.text_mode_3.cursor_x;
+		screen_info->orig_y = info->u.text_mode_3.cursor_y;
+		screen_info->orig_video_points =
+			info->u.text_mode_3.font_height;
+		break;
+
+	case XEN_VGATYPE_VESA_LFB:
+		if (size < offsetof(struct dom0_vga_console_info,
+				    u.vesa_lfb.gbl_caps))
+			break;
+		screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB;
+		screen_info->lfb_width = info->u.vesa_lfb.width;
+		screen_info->lfb_height = info->u.vesa_lfb.height;
+		screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel;
+		screen_info->lfb_base = info->u.vesa_lfb.lfb_base;
+		screen_info->lfb_size = info->u.vesa_lfb.lfb_size;
+		screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line;
+		screen_info->red_size = info->u.vesa_lfb.red_size;
+		screen_info->red_pos = info->u.vesa_lfb.red_pos;
+		screen_info->green_size = info->u.vesa_lfb.green_size;
+		screen_info->green_pos = info->u.vesa_lfb.green_pos;
+		screen_info->blue_size = info->u.vesa_lfb.blue_size;
+		screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
+		screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
+		screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.gbl_caps)
+		    + sizeof(info->u.vesa_lfb.gbl_caps))
+			screen_info->capabilities = info->u.vesa_lfb.gbl_caps;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.mode_attrs)
+		    + sizeof(info->u.vesa_lfb.mode_attrs))
+			screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs;
+		break;
+	}
+}

arch/x86/xen/xen-ops.h

@@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu)
 }
 #endif
 
+struct dom0_vga_console_info;
+
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#else
+static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
+				       size_t size)
+{
+}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\

drivers/block/xen-blkback/xenbus.c

@@ -684,7 +684,7 @@ again:
 
 	err = xenbus_switch_state(dev, XenbusStateConnected);
 	if (err)
-		xenbus_dev_fatal(dev, err, "switching to Connected state",
+		xenbus_dev_fatal(dev, err, "%s: switching to Connected state",
 				 dev->nodename);
 
 	return;

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

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

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
+
+#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 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)
 {
-	struct cleancache_ops old_ops;
-
 	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 "

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;
 

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

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();
+}

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__ */

drivers/xen/xen-pciback/conf_space_capability.c

@@ -0,0 +1,207 @@
+/*
+ * PCI Backend - Handles the virtual fields found on the capability lists
+ *               in the configuration space.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+
+static LIST_HEAD(capabilities);
+struct xen_pcibk_config_capability {
+	struct list_head cap_list;
+
+	int capability;
+
+	/* If the device has the capability found above, add these fields */
+	const struct config_field *fields;
+};
+
+static const struct config_field caplist_header[] = {
+	{
+	 .offset    = PCI_CAP_LIST_ID,
+	 .size      = 2, /* encompass PCI_CAP_LIST_ID & PCI_CAP_LIST_NEXT */
+	 .u.w.read  = xen_pcibk_read_config_word,
+	 .u.w.write = NULL,
+	},
+	{}
+};
+
+static inline void register_capability(struct xen_pcibk_config_capability *cap)
+{
+	list_add_tail(&cap->cap_list, &capabilities);
+}
+
+int xen_pcibk_config_capability_add_fields(struct pci_dev *dev)
+{
+	int err = 0;
+	struct xen_pcibk_config_capability *cap;
+	int cap_offset;
+
+	list_for_each_entry(cap, &capabilities, cap_list) {
+		cap_offset = pci_find_capability(dev, cap->capability);
+		if (cap_offset) {
+			dev_dbg(&dev->dev, "Found capability 0x%x at 0x%x\n",
+				cap->capability, cap_offset);
+
+			err = xen_pcibk_config_add_fields_offset(dev,
+							       caplist_header,
+							       cap_offset);
+			if (err)
+				goto out;
+			err = xen_pcibk_config_add_fields_offset(dev,
+							       cap->fields,
+							       cap_offset);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	return err;
+}
+
+static int vpd_address_write(struct pci_dev *dev, int offset, u16 value,
+			     void *data)
+{
+	/* Disallow writes to the vital product data */
+	if (value & PCI_VPD_ADDR_F)
+		return PCIBIOS_SET_FAILED;
+	else
+		return pci_write_config_word(dev, offset, value);
+}
+
+static const struct config_field caplist_vpd[] = {
+	{
+	 .offset    = PCI_VPD_ADDR,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_config_word,
+	 .u.w.write = vpd_address_write,
+	 },
+	{
+	 .offset     = PCI_VPD_DATA,
+	 .size       = 4,
+	 .u.dw.read  = xen_pcibk_read_config_dword,
+	 .u.dw.write = NULL,
+	 },
+	{}
+};
+
+static int pm_caps_read(struct pci_dev *dev, int offset, u16 *value,
+			void *data)
+{
+	int err;
+	u16 real_value;
+
+	err = pci_read_config_word(dev, offset, &real_value);
+	if (err)
+		goto out;
+
+	*value = real_value & ~PCI_PM_CAP_PME_MASK;
+
+out:
+	return err;
+}
+
+/* PM_OK_BITS specifies the bits that the driver domain is allowed to change.
+ * Can't allow driver domain to enable PMEs - they're shared */
+#define PM_OK_BITS (PCI_PM_CTRL_PME_STATUS|PCI_PM_CTRL_DATA_SEL_MASK)
+
+static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value,
+			 void *data)
+{
+	int err;
+	u16 old_value;
+	pci_power_t new_state, old_state;
+
+	err = pci_read_config_word(dev, offset, &old_value);
+	if (err)
+		goto out;
+
+	old_state = (pci_power_t)(old_value & PCI_PM_CTRL_STATE_MASK);
+	new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
+
+	new_value &= PM_OK_BITS;
+	if ((old_value & PM_OK_BITS) != new_value) {
+		new_value = (old_value & ~PM_OK_BITS) | new_value;
+		err = pci_write_config_word(dev, offset, new_value);
+		if (err)
+			goto out;
+	}
+
+	/* Let pci core handle the power management change */
+	dev_dbg(&dev->dev, "set power state to %x\n", new_state);
+	err = pci_set_power_state(dev, new_state);
+	if (err) {
+		err = PCIBIOS_SET_FAILED;
+		goto out;
+	}
+
+ out:
+	return err;
+}
+
+/* Ensure PMEs are disabled */
+static void *pm_ctrl_init(struct pci_dev *dev, int offset)
+{
+	int err;
+	u16 value;
+
+	err = pci_read_config_word(dev, offset, &value);
+	if (err)
+		goto out;
+
+	if (value & PCI_PM_CTRL_PME_ENABLE) {
+		value &= ~PCI_PM_CTRL_PME_ENABLE;
+		err = pci_write_config_word(dev, offset, value);
+	}
+
+out:
+	return ERR_PTR(err);
+}
+
+static const struct config_field caplist_pm[] = {
+	{
+		.offset     = PCI_PM_PMC,
+		.size       = 2,
+		.u.w.read   = pm_caps_read,
+	},
+	{
+		.offset     = PCI_PM_CTRL,
+		.size       = 2,
+		.init       = pm_ctrl_init,
+		.u.w.read   = xen_pcibk_read_config_word,
+		.u.w.write  = pm_ctrl_write,
+	},
+	{
+		.offset     = PCI_PM_PPB_EXTENSIONS,
+		.size       = 1,
+		.u.b.read   = xen_pcibk_read_config_byte,
+	},
+	{
+		.offset     = PCI_PM_DATA_REGISTER,
+		.size       = 1,
+		.u.b.read   = xen_pcibk_read_config_byte,
+	},
+	{}
+};
+
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_pm = {
+	.capability = PCI_CAP_ID_PM,
+	.fields = caplist_pm,
+};
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_vpd = {
+	.capability = PCI_CAP_ID_VPD,
+	.fields = caplist_vpd,
+};
+
+int xen_pcibk_config_capability_init(void)
+{
+	register_capability(&xen_pcibk_config_capability_vpd);
+	register_capability(&xen_pcibk_config_capability_pm);
+
+	return 0;
+}

drivers/xen/xen-pciback/conf_space_header.c

@@ -0,0 +1,386 @@
+/*
+ * PCI Backend - Handles the virtual fields in the configuration space headers.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+
+struct pci_bar_info {
+	u32 val;
+	u32 len_val;
+	int which;
+};
+
+#define DRV_NAME	"xen-pciback"
+#define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO))
+#define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER)
+
+static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+{
+	int i;
+	int ret;
+
+	ret = xen_pcibk_read_config_word(dev, offset, value, data);
+	if (!atomic_read(&dev->enable_cnt))
+		return ret;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		if (dev->resource[i].flags & IORESOURCE_IO)
+			*value |= PCI_COMMAND_IO;
+		if (dev->resource[i].flags & IORESOURCE_MEM)
+			*value |= PCI_COMMAND_MEMORY;
+	}
+
+	return ret;
+}
+
+static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int err;
+
+	dev_data = pci_get_drvdata(dev);
+	if (!pci_is_enabled(dev) && is_enable_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: enable\n",
+			       pci_name(dev));
+		err = pci_enable_device(dev);
+		if (err)
+			return err;
+		if (dev_data)
+			dev_data->enable_intx = 1;
+	} else if (pci_is_enabled(dev) && !is_enable_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: disable\n",
+			       pci_name(dev));
+		pci_disable_device(dev);
+		if (dev_data)
+			dev_data->enable_intx = 0;
+	}
+
+	if (!dev->is_busmaster && is_master_cmd(value)) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG DRV_NAME ": %s: set bus master\n",
+			       pci_name(dev));
+		pci_set_master(dev);
+	}
+
+	if (value & PCI_COMMAND_INVALIDATE) {
+		if (unlikely(verbose_request))
+			printk(KERN_DEBUG
+			       DRV_NAME ": %s: enable memory-write-invalidate\n",
+			       pci_name(dev));
+		err = pci_set_mwi(dev);
+		if (err) {
+			printk(KERN_WARNING
+			       DRV_NAME ": %s: cannot enable "
+			       "memory-write-invalidate (%d)\n",
+			       pci_name(dev), err);
+			value &= ~PCI_COMMAND_INVALIDATE;
+		}
+	}
+
+	return pci_write_config_word(dev, offset, value);
+}
+
+static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* A write to obtain the length must happen as a 32-bit write.
+	 * This does not (yet) support writing individual bytes
+	 */
+	if (value == ~PCI_ROM_ADDRESS_ENABLE)
+		bar->which = 1;
+	else {
+		u32 tmpval;
+		pci_read_config_dword(dev, offset, &tmpval);
+		if (tmpval != bar->val && value == bar->val) {
+			/* Allow restoration of bar value. */
+			pci_write_config_dword(dev, offset, bar->val);
+		}
+		bar->which = 0;
+	}
+
+	/* Do we need to support enabling/disabling the rom address here? */
+
+	return 0;
+}
+
+/* For the BARs, only allow writes which write ~0 or
+ * the correct resource information
+ * (Needed for when the driver probes the resource usage)
+ */
+static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* A write to obtain the length must happen as a 32-bit write.
+	 * This does not (yet) support writing individual bytes
+	 */
+	if (value == ~0)
+		bar->which = 1;
+	else {
+		u32 tmpval;
+		pci_read_config_dword(dev, offset, &tmpval);
+		if (tmpval != bar->val && value == bar->val) {
+			/* Allow restoration of bar value. */
+			pci_write_config_dword(dev, offset, bar->val);
+		}
+		bar->which = 0;
+	}
+
+	return 0;
+}
+
+static int bar_read(struct pci_dev *dev, int offset, u32 * value, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	if (unlikely(!bar)) {
+		printk(KERN_WARNING DRV_NAME ": driver data not found for %s\n",
+		       pci_name(dev));
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	*value = bar->which ? bar->len_val : bar->val;
+
+	return 0;
+}
+
+static inline void read_dev_bar(struct pci_dev *dev,
+				struct pci_bar_info *bar_info, int offset,
+				u32 len_mask)
+{
+	int	pos;
+	struct resource	*res = dev->resource;
+
+	if (offset == PCI_ROM_ADDRESS || offset == PCI_ROM_ADDRESS1)
+		pos = PCI_ROM_RESOURCE;
+	else {
+		pos = (offset - PCI_BASE_ADDRESS_0) / 4;
+		if (pos && ((res[pos - 1].flags & (PCI_BASE_ADDRESS_SPACE |
+				PCI_BASE_ADDRESS_MEM_TYPE_MASK)) ==
+			   (PCI_BASE_ADDRESS_SPACE_MEMORY |
+				PCI_BASE_ADDRESS_MEM_TYPE_64))) {
+			bar_info->val = res[pos - 1].start >> 32;
+			bar_info->len_val = res[pos - 1].end >> 32;
+			return;
+		}
+	}
+
+	bar_info->val = res[pos].start |
+			(res[pos].flags & PCI_REGION_FLAG_MASK);
+	bar_info->len_val = res[pos].end - res[pos].start + 1;
+}
+
+static void *bar_init(struct pci_dev *dev, int offset)
+{
+	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+
+	if (!bar)
+		return ERR_PTR(-ENOMEM);
+
+	read_dev_bar(dev, bar, offset, ~0);
+	bar->which = 0;
+
+	return bar;
+}
+
+static void *rom_init(struct pci_dev *dev, int offset)
+{
+	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+
+	if (!bar)
+		return ERR_PTR(-ENOMEM);
+
+	read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE);
+	bar->which = 0;
+
+	return bar;
+}
+
+static void bar_reset(struct pci_dev *dev, int offset, void *data)
+{
+	struct pci_bar_info *bar = data;
+
+	bar->which = 0;
+}
+
+static void bar_release(struct pci_dev *dev, int offset, void *data)
+{
+	kfree(data);
+}
+
+static int xen_pcibk_read_vendor(struct pci_dev *dev, int offset,
+			       u16 *value, void *data)
+{
+	*value = dev->vendor;
+
+	return 0;
+}
+
+static int xen_pcibk_read_device(struct pci_dev *dev, int offset,
+			       u16 *value, void *data)
+{
+	*value = dev->device;
+
+	return 0;
+}
+
+static int interrupt_read(struct pci_dev *dev, int offset, u8 * value,
+			  void *data)
+{
+	*value = (u8) dev->irq;
+
+	return 0;
+}
+
+static int bist_write(struct pci_dev *dev, int offset, u8 value, void *data)
+{
+	u8 cur_value;
+	int err;
+
+	err = pci_read_config_byte(dev, offset, &cur_value);
+	if (err)
+		goto out;
+
+	if ((cur_value & ~PCI_BIST_START) == (value & ~PCI_BIST_START)
+	    || value == PCI_BIST_START)
+		err = pci_write_config_byte(dev, offset, value);
+
+out:
+	return err;
+}
+
+static const struct config_field header_common[] = {
+	{
+	 .offset    = PCI_VENDOR_ID,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_vendor,
+	},
+	{
+	 .offset    = PCI_DEVICE_ID,
+	 .size      = 2,
+	 .u.w.read  = xen_pcibk_read_device,
+	},
+	{
+	 .offset    = PCI_COMMAND,
+	 .size      = 2,
+	 .u.w.read  = command_read,
+	 .u.w.write = command_write,
+	},
+	{
+	 .offset    = PCI_INTERRUPT_LINE,
+	 .size      = 1,
+	 .u.b.read  = interrupt_read,
+	},
+	{
+	 .offset    = PCI_INTERRUPT_PIN,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	},
+	{
+	 /* Any side effects of letting driver domain control cache line? */
+	 .offset    = PCI_CACHE_LINE_SIZE,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	 .u.b.write = xen_pcibk_write_config_byte,
+	},
+	{
+	 .offset    = PCI_LATENCY_TIMER,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	},
+	{
+	 .offset    = PCI_BIST,
+	 .size      = 1,
+	 .u.b.read  = xen_pcibk_read_config_byte,
+	 .u.b.write = bist_write,
+	},
+	{}
+};
+
+#define CFG_FIELD_BAR(reg_offset)			\
+	{						\
+	.offset     = reg_offset,			\
+	.size       = 4,				\
+	.init       = bar_init,				\
+	.reset      = bar_reset,			\
+	.release    = bar_release,			\
+	.u.dw.read  = bar_read,				\
+	.u.dw.write = bar_write,			\
+	}
+
+#define CFG_FIELD_ROM(reg_offset)			\
+	{						\
+	.offset     = reg_offset,			\
+	.size       = 4,				\
+	.init       = rom_init,				\
+	.reset      = bar_reset,			\
+	.release    = bar_release,			\
+	.u.dw.read  = bar_read,				\
+	.u.dw.write = rom_write,			\
+	}
+
+static const struct config_field header_0[] = {
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_0),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_1),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_2),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_3),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_4),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_5),
+	CFG_FIELD_ROM(PCI_ROM_ADDRESS),
+	{}
+};
+
+static const struct config_field header_1[] = {
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_0),
+	CFG_FIELD_BAR(PCI_BASE_ADDRESS_1),
+	CFG_FIELD_ROM(PCI_ROM_ADDRESS1),
+	{}
+};
+
+int xen_pcibk_config_header_add_fields(struct pci_dev *dev)
+{
+	int err;
+
+	err = xen_pcibk_config_add_fields(dev, header_common);
+	if (err)
+		goto out;
+
+	switch (dev->hdr_type) {
+	case PCI_HEADER_TYPE_NORMAL:
+		err = xen_pcibk_config_add_fields(dev, header_0);
+		break;
+
+	case PCI_HEADER_TYPE_BRIDGE:
+		err = xen_pcibk_config_add_fields(dev, header_1);
+		break;
+
+	default:
+		err = -EINVAL;
+		printk(KERN_ERR DRV_NAME ": %s: Unsupported header type %d!\n",
+		       pci_name(dev), dev->hdr_type);
+		break;
+	}
+
+out:
+	return err;
+}

drivers/xen/xen-pciback/conf_space_quirks.c

@@ -0,0 +1,140 @@
+/*
+ * PCI Backend - Handle special overlays for broken devices.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Author: Chris Bookholt <hap10@epoch.ncsc.mil>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include "pciback.h"
+#include "conf_space.h"
+#include "conf_space_quirks.h"
+
+LIST_HEAD(xen_pcibk_quirks);
+#define	DRV_NAME	"xen-pciback"
+static inline const struct pci_device_id *
+match_one_device(const struct pci_device_id *id, const struct pci_dev *dev)
+{
+	if ((id->vendor == PCI_ANY_ID || id->vendor == dev->vendor) &&
+	    (id->device == PCI_ANY_ID || id->device == dev->device) &&
+	    (id->subvendor == PCI_ANY_ID ||
+				id->subvendor == dev->subsystem_vendor) &&
+	    (id->subdevice == PCI_ANY_ID ||
+				id->subdevice == dev->subsystem_device) &&
+	    !((id->class ^ dev->class) & id->class_mask))
+		return id;
+	return NULL;
+}
+
+static struct xen_pcibk_config_quirk *xen_pcibk_find_quirk(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *tmp_quirk;
+
+	list_for_each_entry(tmp_quirk, &xen_pcibk_quirks, quirks_list)
+		if (match_one_device(&tmp_quirk->devid, dev) != NULL)
+			goto out;
+	tmp_quirk = NULL;
+	printk(KERN_DEBUG DRV_NAME
+	       ":quirk didn't match any device xen_pciback knows about\n");
+out:
+	return tmp_quirk;
+}
+
+static inline void register_quirk(struct xen_pcibk_config_quirk *quirk)
+{
+	list_add_tail(&quirk->quirks_list, &xen_pcibk_quirks);
+}
+
+int xen_pcibk_field_is_dup(struct pci_dev *dev, unsigned int reg)
+{
+	int ret = 0;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+	struct config_field_entry *cfg_entry;
+
+	list_for_each_entry(cfg_entry, &dev_data->config_fields, list) {
+		if (OFFSET(cfg_entry) == reg) {
+			ret = 1;
+			break;
+		}
+	}
+	return ret;
+}
+
+int xen_pcibk_config_quirks_add_field(struct pci_dev *dev, struct config_field
+				    *field)
+{
+	int err = 0;
+
+	switch (field->size) {
+	case 1:
+		field->u.b.read = xen_pcibk_read_config_byte;
+		field->u.b.write = xen_pcibk_write_config_byte;
+		break;
+	case 2:
+		field->u.w.read = xen_pcibk_read_config_word;
+		field->u.w.write = xen_pcibk_write_config_word;
+		break;
+	case 4:
+		field->u.dw.read = xen_pcibk_read_config_dword;
+		field->u.dw.write = xen_pcibk_write_config_dword;
+		break;
+	default:
+		err = -EINVAL;
+		goto out;
+	}
+
+	xen_pcibk_config_add_field(dev, field);
+
+out:
+	return err;
+}
+
+int xen_pcibk_config_quirks_init(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *quirk;
+	int ret = 0;
+
+	quirk = kzalloc(sizeof(*quirk), GFP_ATOMIC);
+	if (!quirk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	quirk->devid.vendor = dev->vendor;
+	quirk->devid.device = dev->device;
+	quirk->devid.subvendor = dev->subsystem_vendor;
+	quirk->devid.subdevice = dev->subsystem_device;
+	quirk->devid.class = 0;
+	quirk->devid.class_mask = 0;
+	quirk->devid.driver_data = 0UL;
+
+	quirk->pdev = dev;
+
+	register_quirk(quirk);
+out:
+	return ret;
+}
+
+void xen_pcibk_config_field_free(struct config_field *field)
+{
+	kfree(field);
+}
+
+int xen_pcibk_config_quirk_release(struct pci_dev *dev)
+{
+	struct xen_pcibk_config_quirk *quirk;
+	int ret = 0;
+
+	quirk = xen_pcibk_find_quirk(dev);
+	if (!quirk) {
+		ret = -ENXIO;
+		goto out;
+	}
+
+	list_del(&quirk->quirks_list);
+	kfree(quirk);
+
+out:
+	return ret;
+}

drivers/xen/xen-pciback/conf_space_quirks.h

@@ -0,0 +1,33 @@
+/*
+ * PCI Backend - Data structures for special overlays for broken devices.
+ *
+ * Ryan Wilson <hap9@epoch.ncsc.mil>
+ * Chris Bookholt <hap10@epoch.ncsc.mil>
+ */
+
+#ifndef __XEN_PCIBACK_CONF_SPACE_QUIRKS_H__
+#define __XEN_PCIBACK_CONF_SPACE_QUIRKS_H__
+
+#include <linux/pci.h>
+#include <linux/list.h>
+
+struct xen_pcibk_config_quirk {
+	struct list_head quirks_list;
+	struct pci_device_id devid;
+	struct pci_dev *pdev;
+};
+
+int xen_pcibk_config_quirks_add_field(struct pci_dev *dev, struct config_field
+				    *field);
+
+int xen_pcibk_config_quirks_remove_field(struct pci_dev *dev, int reg);
+
+int xen_pcibk_config_quirks_init(struct pci_dev *dev);
+
+void xen_pcibk_config_field_free(struct config_field *field);
+
+int xen_pcibk_config_quirk_release(struct pci_dev *dev);
+
+int xen_pcibk_field_is_dup(struct pci_dev *dev, unsigned int reg);
+
+#endif

drivers/xen/xen-pciback/passthrough.c

@@ -0,0 +1,194 @@
+/*
+ * 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;
+};
+
+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;
+	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;
+}
+
+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;
+	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;
+}
+
+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;
+	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);
+}
+
+static int __xen_pcibk_init_devices(struct xen_pcibk_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;
+}
+
+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;
+	struct pci_dev_entry *dev_entry, *e, *tmp;
+	struct pci_dev *dev;
+	int found;
+	unsigned int domain, bus;
+
+	spin_lock(&dev_data->lock);
+
+	list_for_each_entry_safe(dev_entry, tmp, &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) {
+			spin_unlock(&dev_data->lock);
+			err = publish_root_cb(pdev, domain, bus);
+			if (err)
+				break;
+			spin_lock(&dev_data->lock);
+		}
+	}
+
+	if (!err)
+		spin_unlock(&dev_data->lock);
+
+	return err;
+}
+
+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;
+
+	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;
+}
+
+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

@@ -0,0 +1,183 @@
+/*
+ * PCI Backend Common Data Structures & Function Declarations
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCIBACK_H__
+#define __XEN_PCIBACK_H__
+
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <xen/xenbus.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/atomic.h>
+#include <xen/interface/io/pciif.h>
+
+struct pci_dev_entry {
+	struct list_head list;
+	struct pci_dev *dev;
+};
+
+#define _PDEVF_op_active	(0)
+#define PDEVF_op_active		(1<<(_PDEVF_op_active))
+#define _PCIB_op_pending	(1)
+#define PCIB_op_pending		(1<<(_PCIB_op_pending))
+
+struct xen_pcibk_device {
+	void *pci_dev_data;
+	spinlock_t dev_lock;
+	struct xenbus_device *xdev;
+	struct xenbus_watch be_watch;
+	u8 be_watching;
+	int evtchn_irq;
+	struct xen_pci_sharedinfo *sh_info;
+	unsigned long flags;
+	struct work_struct op_work;
+};
+
+struct xen_pcibk_dev_data {
+	struct list_head config_fields;
+	unsigned int permissive:1;
+	unsigned int warned_on_write:1;
+	unsigned int enable_intx:1;
+	unsigned int isr_on:1; /* Whether the IRQ handler is installed. */
+	unsigned int ack_intr:1; /* .. and ACK-ing */
+	unsigned long handled;
+	unsigned int irq; /* Saved in case device transitions to MSI/MSI-X */
+	char irq_name[0]; /* xen-pcibk[000:04:00.0] */
+};
+
+/* Used by XenBus and xen_pcibk_ops.c */
+extern wait_queue_head_t xen_pcibk_aer_wait_queue;
+extern struct workqueue_struct *xen_pcibk_wq;
+/* Used by pcistub.c and conf_space_quirks.c */
+extern struct list_head xen_pcibk_quirks;
+
+/* Get/Put PCI Devices that are hidden from the PCI Backend Domain */
+struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
+					    int domain, int bus,
+					    int slot, int func);
+struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
+				    struct pci_dev *dev);
+void pcistub_put_pci_dev(struct pci_dev *dev);
+
+/* Ensure a device is turned off or reset */
+void xen_pcibk_reset_device(struct pci_dev *pdev);
+
+/* Access a virtual configuration space for a PCI device */
+int xen_pcibk_config_init(void);
+int xen_pcibk_config_init_dev(struct pci_dev *dev);
+void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev);
+void xen_pcibk_config_reset_dev(struct pci_dev *dev);
+void xen_pcibk_config_free_dev(struct pci_dev *dev);
+int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
+			  u32 *ret_val);
+int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size,
+			   u32 value);
+
+/* Handle requests for specific devices from the frontend */
+typedef int (*publish_pci_dev_cb) (struct xen_pcibk_device *pdev,
+				   unsigned int domain, unsigned int bus,
+				   unsigned int devfn, unsigned int devid);
+typedef int (*publish_pci_root_cb) (struct xen_pcibk_device *pdev,
+				    unsigned int domain, unsigned int bus);
+
+/* 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
+*/
+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);
+
+int xen_pcibk_xenbus_register(void);
+void xen_pcibk_xenbus_unregister(void);
+
+extern int verbose_request;
+
+void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev);
+#endif
+
+/* Handles shared IRQs that can to device domain and control domain. */
+void xen_pcibk_irq_handler(struct pci_dev *dev, int reset);

drivers/xen/xen-pciback/pciback_ops.c

@@ -0,0 +1,384 @@
+/*
+ * PCI Backend Operations - respond to PCI requests from Frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/bitops.h>
+#include <xen/events.h>
+#include <linux/sched.h>
+#include "pciback.h"
+
+#define DRV_NAME	"xen-pciback"
+int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id);
+
+/* Ensure a device is has the fake IRQ handler "turned on/off" and is
+ * ready to be exported. This MUST be run after xen_pcibk_reset_device
+ * which does the actual PCI device enable/disable.
+ */
+static void xen_pcibk_control_isr(struct pci_dev *dev, int reset)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int rc;
+	int enable = 0;
+
+	dev_data = pci_get_drvdata(dev);
+	if (!dev_data)
+		return;
+
+	/* We don't deal with bridges */
+	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
+		return;
+
+	if (reset) {
+		dev_data->enable_intx = 0;
+		dev_data->ack_intr = 0;
+	}
+	enable =  dev_data->enable_intx;
+
+	/* Asked to disable, but ISR isn't runnig */
+	if (!enable && !dev_data->isr_on)
+		return;
+
+	/* Squirrel away the IRQs in the dev_data. We need this
+	 * b/c when device transitions to MSI, the dev->irq is
+	 * overwritten with the MSI vector.
+	 */
+	if (enable)
+		dev_data->irq = dev->irq;
+
+	/*
+	 * SR-IOV devices in all use MSI-X and have no legacy
+	 * interrupts, so inhibit creating a fake IRQ handler for them.
+	 */
+	if (dev_data->irq == 0)
+		goto out;
+
+	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s-> %s\n",
+		dev_data->irq_name,
+		dev_data->irq,
+		pci_is_enabled(dev) ? "on" : "off",
+		dev->msi_enabled ? "MSI" : "",
+		dev->msix_enabled ? "MSI/X" : "",
+		dev_data->isr_on ? "enable" : "disable",
+		enable ? "enable" : "disable");
+
+	if (enable) {
+		rc = request_irq(dev_data->irq,
+				xen_pcibk_guest_interrupt, IRQF_SHARED,
+				dev_data->irq_name, dev);
+		if (rc) {
+			dev_err(&dev->dev, "%s: failed to install fake IRQ " \
+				"handler for IRQ %d! (rc:%d)\n",
+				dev_data->irq_name, dev_data->irq, rc);
+			goto out;
+		}
+	} else {
+		free_irq(dev_data->irq, dev);
+		dev_data->irq = 0;
+	}
+	dev_data->isr_on = enable;
+	dev_data->ack_intr = enable;
+out:
+	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s\n",
+		dev_data->irq_name,
+		dev_data->irq,
+		pci_is_enabled(dev) ? "on" : "off",
+		dev->msi_enabled ? "MSI" : "",
+		dev->msix_enabled ? "MSI/X" : "",
+		enable ? (dev_data->isr_on ? "enabled" : "failed to enable") :
+			(dev_data->isr_on ? "failed to disable" : "disabled"));
+}
+
+/* Ensure a device is "turned off" and ready to be exported.
+ * (Also see xen_pcibk_config_reset to ensure virtual configuration space is
+ * ready to be re-exported)
+ */
+void xen_pcibk_reset_device(struct pci_dev *dev)
+{
+	u16 cmd;
+
+	xen_pcibk_control_isr(dev, 1 /* reset device */);
+
+	/* Disable devices (but not bridges) */
+	if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
+#ifdef CONFIG_PCI_MSI
+		/* The guest could have been abruptly killed without
+		 * disabling MSI/MSI-X interrupts.*/
+		if (dev->msix_enabled)
+			pci_disable_msix(dev);
+		if (dev->msi_enabled)
+			pci_disable_msi(dev);
+#endif
+		pci_disable_device(dev);
+
+		pci_write_config_word(dev, PCI_COMMAND, 0);
+
+		dev->is_busmaster = 0;
+	} else {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & (PCI_COMMAND_INVALIDATE)) {
+			cmd &= ~(PCI_COMMAND_INVALIDATE);
+			pci_write_config_word(dev, PCI_COMMAND, cmd);
+
+			dev->is_busmaster = 0;
+		}
+	}
+}
+
+#ifdef CONFIG_PCI_MSI
+static
+int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev,
+			 struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int otherend = pdev->xdev->otherend_id;
+	int status;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI\n", pci_name(dev));
+
+	status = pci_enable_msi(dev);
+
+	if (status) {
+		printk(KERN_ERR "error enable msi for guest %x status %x\n",
+			otherend, status);
+		op->value = 0;
+		return XEN_PCI_ERR_op_failed;
+	}
+
+	/* The value the guest needs is actually the IDT vector, not the
+	 * the local domain's IRQ number. */
+
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
+			op->value);
+
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 0;
+
+	return 0;
+}
+
+static
+int xen_pcibk_disable_msi(struct xen_pcibk_device *pdev,
+			  struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI\n",
+		       pci_name(dev));
+	pci_disable_msi(dev);
+
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
+			op->value);
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 1;
+	return 0;
+}
+
+static
+int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
+			  struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	int i, result;
+	struct msix_entry *entries;
+
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n",
+		       pci_name(dev));
+	if (op->value > SH_INFO_MAX_VEC)
+		return -EINVAL;
+
+	entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL);
+	if (entries == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < op->value; i++) {
+		entries[i].entry = op->msix_entries[i].entry;
+		entries[i].vector = op->msix_entries[i].vector;
+	}
+
+	result = pci_enable_msix(dev, entries, op->value);
+
+	if (result == 0) {
+		for (i = 0; i < op->value; i++) {
+			op->msix_entries[i].entry = entries[i].entry;
+			if (entries[i].vector)
+				op->msix_entries[i].vector =
+					xen_pirq_from_irq(entries[i].vector);
+				if (unlikely(verbose_request))
+					printk(KERN_DEBUG DRV_NAME ": %s: " \
+						"MSI-X[%d]: %d\n",
+						pci_name(dev), i,
+						op->msix_entries[i].vector);
+		}
+	} else {
+		printk(KERN_WARNING DRV_NAME ": %s: failed to enable MSI-X: err %d!\n",
+			pci_name(dev), result);
+	}
+	kfree(entries);
+
+	op->value = result;
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 0;
+
+	return result;
+}
+
+static
+int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev,
+			   struct pci_dev *dev, struct xen_pci_op *op)
+{
+	struct xen_pcibk_dev_data *dev_data;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI-X\n",
+			pci_name(dev));
+	pci_disable_msix(dev);
+
+	/*
+	 * SR-IOV devices (which don't have any legacy IRQ) have
+	 * an undefined IRQ value of zero.
+	 */
+	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
+	if (unlikely(verbose_request))
+		printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n", pci_name(dev),
+			op->value);
+	dev_data = pci_get_drvdata(dev);
+	if (dev_data)
+		dev_data->ack_intr = 1;
+	return 0;
+}
+#endif
+/*
+* Now the same evtchn is used for both pcifront conf_read_write request
+* as well as pcie aer front end ack. We use a new work_queue to schedule
+* xen_pcibk conf_read_write service for avoiding confict with aer_core
+* do_recovery job which also use the system default work_queue
+*/
+void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev)
+{
+	/* Check that frontend is requesting an operation and that we are not
+	 * already processing a request */
+	if (test_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags)
+	    && !test_and_set_bit(_PDEVF_op_active, &pdev->flags)) {
+		queue_work(xen_pcibk_wq, &pdev->op_work);
+	}
+	/*_XEN_PCIB_active should have been cleared by pcifront. And also make
+	sure xen_pcibk is waiting for ack by checking _PCIB_op_pending*/
+	if (!test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+	    && test_bit(_PCIB_op_pending, &pdev->flags)) {
+		wake_up(&xen_pcibk_aer_wait_queue);
+	}
+}
+
+/* Performing the configuration space reads/writes must not be done in atomic
+ * context because some of the pci_* functions can sleep (mostly due to ACPI
+ * use of semaphores). This function is intended to be called from a work
+ * queue in process context taking a struct xen_pcibk_device as a parameter */
+
+void xen_pcibk_do_op(struct work_struct *data)
+{
+	struct xen_pcibk_device *pdev =
+		container_of(data, struct xen_pcibk_device, op_work);
+	struct pci_dev *dev;
+	struct xen_pcibk_dev_data *dev_data = NULL;
+	struct xen_pci_op *op = &pdev->sh_info->op;
+	int test_intx = 0;
+
+	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);
+
+	if (dev == NULL)
+		op->err = XEN_PCI_ERR_dev_not_found;
+	else {
+		dev_data = pci_get_drvdata(dev);
+		if (dev_data)
+			test_intx = dev_data->enable_intx;
+		switch (op->cmd) {
+		case XEN_PCI_OP_conf_read:
+			op->err = xen_pcibk_config_read(dev,
+				  op->offset, op->size, &op->value);
+			break;
+		case XEN_PCI_OP_conf_write:
+			op->err = xen_pcibk_config_write(dev,
+				  op->offset, op->size,	op->value);
+			break;
+#ifdef CONFIG_PCI_MSI
+		case XEN_PCI_OP_enable_msi:
+			op->err = xen_pcibk_enable_msi(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_disable_msi:
+			op->err = xen_pcibk_disable_msi(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_enable_msix:
+			op->err = xen_pcibk_enable_msix(pdev, dev, op);
+			break;
+		case XEN_PCI_OP_disable_msix:
+			op->err = xen_pcibk_disable_msix(pdev, dev, op);
+			break;
+#endif
+		default:
+			op->err = XEN_PCI_ERR_not_implemented;
+			break;
+		}
+	}
+	if (!op->err && dev && dev_data) {
+		/* Transition detected */
+		if ((dev_data->enable_intx != test_intx))
+			xen_pcibk_control_isr(dev, 0 /* no reset */);
+	}
+	/* Tell the driver domain that we're done. */
+	wmb();
+	clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_irq(pdev->evtchn_irq);
+
+	/* Mark that we're done. */
+	smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */
+	clear_bit(_PDEVF_op_active, &pdev->flags);
+	smp_mb__after_clear_bit(); /* /before/ final check for work */
+
+	/* Check to see if the driver domain tried to start another request in
+	 * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.
+	*/
+	xen_pcibk_test_and_schedule_op(pdev);
+}
+
+irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id)
+{
+	struct xen_pcibk_device *pdev = dev_id;
+
+	xen_pcibk_test_and_schedule_op(pdev);
+
+	return IRQ_HANDLED;
+}
+static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id)
+{
+	struct pci_dev *dev = (struct pci_dev *)dev_id;
+	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+
+	if (dev_data->isr_on && dev_data->ack_intr) {
+		dev_data->handled++;
+		if ((dev_data->handled % 1000) == 0) {
+			if (xen_test_irq_shared(irq)) {
+				printk(KERN_INFO "%s IRQ line is not shared "
+					"with other domains. Turning ISR off\n",
+					 dev_data->irq_name);
+				dev_data->ack_intr = 0;
+			}
+		}
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}

drivers/xen/xen-pciback/vpci.c

@@ -0,0 +1,259 @@
+/*
+ * PCI Backend - Provides a Virtual PCI bus (with real devices)
+ *               to the frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include "pciback.h"
+
+#define PCI_SLOT_MAX 32
+#define DRV_NAME	"xen-pciback"
+
+struct vpci_dev_data {
+	/* Access to dev_list must be protected by lock */
+	struct list_head dev_list[PCI_SLOT_MAX];
+	spinlock_t lock;
+};
+
+static inline struct list_head *list_first(struct list_head *head)
+{
+	return head->next;
+}
+
+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;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+	unsigned long flags;
+
+	if (domain != 0 || bus != 0)
+		return NULL;
+
+	if (PCI_SLOT(devfn) < PCI_SLOT_MAX) {
+		spin_lock_irqsave(&vpci_dev->lock, flags);
+
+		list_for_each_entry(entry,
+				    &vpci_dev->dev_list[PCI_SLOT(devfn)],
+				    list) {
+			if (PCI_FUNC(entry->dev->devfn) == PCI_FUNC(devfn)) {
+				dev = entry->dev;
+				break;
+			}
+		}
+
+		spin_unlock_irqrestore(&vpci_dev->lock, flags);
+	}
+	return dev;
+}
+
+static inline int match_slot(struct pci_dev *l, struct pci_dev *r)
+{
+	if (pci_domain_nr(l->bus) == pci_domain_nr(r->bus)
+	    && l->bus == r->bus && PCI_SLOT(l->devfn) == PCI_SLOT(r->devfn))
+		return 1;
+
+	return 0;
+}
+
+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;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+	unsigned long flags;
+
+	if ((dev->class >> 24) == PCI_BASE_CLASS_BRIDGE) {
+		err = -EFAULT;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Can't export bridges on the virtual PCI bus");
+		goto out;
+	}
+
+	dev_entry = kmalloc(sizeof(*dev_entry), GFP_KERNEL);
+	if (!dev_entry) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error adding entry to virtual PCI bus");
+		goto out;
+	}
+
+	dev_entry->dev = dev;
+
+	spin_lock_irqsave(&vpci_dev->lock, flags);
+
+	/* Keep multi-function devices together on the virtual PCI bus */
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		if (!list_empty(&vpci_dev->dev_list[slot])) {
+			t = list_entry(list_first(&vpci_dev->dev_list[slot]),
+				       struct pci_dev_entry, list);
+
+			if (match_slot(dev, t->dev)) {
+				pr_info(DRV_NAME ": vpci: %s: "
+					"assign to virtual slot %d func %d\n",
+					pci_name(dev), slot,
+					PCI_FUNC(dev->devfn));
+				list_add_tail(&dev_entry->list,
+					      &vpci_dev->dev_list[slot]);
+				func = PCI_FUNC(dev->devfn);
+				goto unlock;
+			}
+		}
+	}
+
+	/* Assign to a new slot on the virtual PCI bus */
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		if (list_empty(&vpci_dev->dev_list[slot])) {
+			printk(KERN_INFO DRV_NAME
+			       ": vpci: %s: assign to virtual slot %d\n",
+			       pci_name(dev), slot);
+			list_add_tail(&dev_entry->list,
+				      &vpci_dev->dev_list[slot]);
+			func = PCI_FUNC(dev->devfn);
+			goto unlock;
+		}
+	}
+
+	err = -ENOMEM;
+	xenbus_dev_fatal(pdev->xdev, err,
+			 "No more space on root virtual PCI bus");
+
+unlock:
+	spin_unlock_irqrestore(&vpci_dev->lock, flags);
+
+	/* Publish this device. */
+	if (!err)
+		err = publish_cb(pdev, 0, 0, PCI_DEVFN(slot, func), devid);
+
+out:
+	return err;
+}
+
+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;
+	struct pci_dev *found_dev = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vpci_dev->lock, flags);
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		struct pci_dev_entry *e, *tmp;
+		list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
+					 list) {
+			if (e->dev == dev) {
+				list_del(&e->list);
+				found_dev = e->dev;
+				kfree(e);
+				goto out;
+			}
+		}
+	}
+
+out:
+	spin_unlock_irqrestore(&vpci_dev->lock, flags);
+
+	if (found_dev)
+		pcistub_put_pci_dev(found_dev);
+}
+
+static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
+{
+	int slot;
+	struct vpci_dev_data *vpci_dev;
+
+	vpci_dev = kmalloc(sizeof(*vpci_dev), GFP_KERNEL);
+	if (!vpci_dev)
+		return -ENOMEM;
+
+	spin_lock_init(&vpci_dev->lock);
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++)
+		INIT_LIST_HEAD(&vpci_dev->dev_list[slot]);
+
+	pdev->pci_dev_data = vpci_dev;
+
+	return 0;
+}
+
+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);
+}
+
+static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
+{
+	int slot;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		struct pci_dev_entry *e, *tmp;
+		list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
+					 list) {
+			list_del(&e->list);
+			pcistub_put_pci_dev(e->dev);
+			kfree(e);
+		}
+	}
+
+	kfree(vpci_dev);
+	pdev->pci_dev_data = NULL;
+}
+
+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;
+	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
+	unsigned long flags;
+	int found = 0, slot;
+
+	spin_lock_irqsave(&vpci_dev->lock, flags);
+	for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+		list_for_each_entry(entry,
+			    &vpci_dev->dev_list[slot],
+			    list) {
+			dev = entry->dev;
+			if (dev && dev->bus->number == pcidev->bus->number
+				&& pci_domain_nr(dev->bus) ==
+					pci_domain_nr(pcidev->bus)
+				&& dev->devfn == pcidev->devfn) {
+				found = 1;
+				*domain = 0;
+				*bus = 0;
+				*devfn = PCI_DEVFN(slot,
+					 PCI_FUNC(pcidev->devfn));
+			}
+		}
+	}
+	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

@@ -0,0 +1,749 @@
+/*
+ * PCI Backend Xenbus Setup - handles setup with frontend and xend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/vmalloc.h>
+#include <linux/workqueue.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <asm/xen/pci.h>
+#include <linux/workqueue.h>
+#include "pciback.h"
+
+#define	DRV_NAME	"xen-pciback"
+#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;
+
+	pdev = kzalloc(sizeof(struct xen_pcibk_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+	dev_dbg(&xdev->dev, "allocated pdev @ 0x%p\n", pdev);
+
+	pdev->xdev = xdev;
+	dev_set_drvdata(&xdev->dev, pdev);
+
+	spin_lock_init(&pdev->dev_lock);
+
+	pdev->sh_info = NULL;
+	pdev->evtchn_irq = INVALID_EVTCHN_IRQ;
+	pdev->be_watching = 0;
+
+	INIT_WORK(&pdev->op_work, xen_pcibk_do_op);
+
+	if (xen_pcibk_init_devices(pdev)) {
+		kfree(pdev);
+		pdev = NULL;
+	}
+out:
+	return pdev;
+}
+
+static void xen_pcibk_disconnect(struct xen_pcibk_device *pdev)
+{
+	spin_lock(&pdev->dev_lock);
+
+	/* Ensure the guest can't trigger our handler before removing devices */
+	if (pdev->evtchn_irq != INVALID_EVTCHN_IRQ) {
+		unbind_from_irqhandler(pdev->evtchn_irq, pdev);
+		pdev->evtchn_irq = INVALID_EVTCHN_IRQ;
+	}
+	spin_unlock(&pdev->dev_lock);
+
+	/* If the driver domain started an op, make sure we complete it
+	 * before releasing the shared memory */
+
+	/* Note, the workqueue does not use spinlocks at all.*/
+	flush_workqueue(xen_pcibk_wq);
+
+	spin_lock(&pdev->dev_lock);
+	if (pdev->sh_info != NULL) {
+		xenbus_unmap_ring_vfree(pdev->xdev, pdev->sh_info);
+		pdev->sh_info = NULL;
+	}
+	spin_unlock(&pdev->dev_lock);
+
+}
+
+static void free_pdev(struct xen_pcibk_device *pdev)
+{
+	if (pdev->be_watching) {
+		unregister_xenbus_watch(&pdev->be_watch);
+		pdev->be_watching = 0;
+	}
+
+	xen_pcibk_disconnect(pdev);
+
+	xen_pcibk_release_devices(pdev);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+	pdev->xdev = NULL;
+
+	kfree(pdev);
+}
+
+static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref,
+			     int remote_evtchn)
+{
+	int err = 0;
+	void *vaddr;
+
+	dev_dbg(&pdev->xdev->dev,
+		"Attaching to frontend resources - gnt_ref=%d evtchn=%d\n",
+		gnt_ref, remote_evtchn);
+
+	err = xenbus_map_ring_valloc(pdev->xdev, gnt_ref, &vaddr);
+	if (err < 0) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				"Error mapping other domain page in ours.");
+		goto out;
+	}
+
+	spin_lock(&pdev->dev_lock);
+	pdev->sh_info = vaddr;
+	spin_unlock(&pdev->dev_lock);
+
+	err = bind_interdomain_evtchn_to_irqhandler(
+		pdev->xdev->otherend_id, remote_evtchn, xen_pcibk_handle_event,
+		0, DRV_NAME, pdev);
+	if (err < 0) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error binding event channel to IRQ");
+		goto out;
+	}
+
+	spin_lock(&pdev->dev_lock);
+	pdev->evtchn_irq = err;
+	spin_unlock(&pdev->dev_lock);
+	err = 0;
+
+	dev_dbg(&pdev->xdev->dev, "Attached!\n");
+out:
+	return err;
+}
+
+static int xen_pcibk_attach(struct xen_pcibk_device *pdev)
+{
+	int err = 0;
+	int gnt_ref, remote_evtchn;
+	char *magic = NULL;
+
+
+	/* Make sure we only do this setup once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	/* Wait for frontend to state that it has published the configuration */
+	if (xenbus_read_driver_state(pdev->xdev->otherend) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "Reading frontend config\n");
+
+	err = xenbus_gather(XBT_NIL, pdev->xdev->otherend,
+			    "pci-op-ref", "%u", &gnt_ref,
+			    "event-channel", "%u", &remote_evtchn,
+			    "magic", NULL, &magic, NULL);
+	if (err) {
+		/* If configuration didn't get read correctly, wait longer */
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading configuration from frontend");
+		goto out;
+	}
+
+	if (magic == NULL || strcmp(magic, XEN_PCI_MAGIC) != 0) {
+		xenbus_dev_fatal(pdev->xdev, -EFAULT,
+				 "version mismatch (%s/%s) with pcifront - "
+				 "halting xen_pcibk",
+				 magic, XEN_PCI_MAGIC);
+		goto out;
+	}
+
+	err = xen_pcibk_do_attach(pdev, gnt_ref, remote_evtchn);
+	if (err)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "Connecting...\n");
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+	if (err)
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to connected state!");
+
+	dev_dbg(&pdev->xdev->dev, "Connected? %d\n", err);
+out:
+
+	kfree(magic);
+
+	return err;
+}
+
+static int xen_pcibk_publish_pci_dev(struct xen_pcibk_device *pdev,
+				   unsigned int domain, unsigned int bus,
+				   unsigned int devfn, unsigned int devid)
+{
+	int err;
+	int len;
+	char str[64];
+
+	len = snprintf(str, sizeof(str), "vdev-%d", devid);
+	if (unlikely(len >= (sizeof(str) - 1))) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str,
+			    "%04x:%02x:%02x.%02x", domain, bus,
+			    PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+out:
+	return err;
+}
+
+static int xen_pcibk_export_device(struct xen_pcibk_device *pdev,
+				 int domain, int bus, int slot, int func,
+				 int devid)
+{
+	struct pci_dev *dev;
+	int err = 0;
+
+	dev_dbg(&pdev->xdev->dev, "exporting dom %x bus %x slot %x func %x\n",
+		domain, bus, slot, func);
+
+	dev = pcistub_get_pci_dev_by_slot(pdev, domain, bus, slot, func);
+	if (!dev) {
+		err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Couldn't locate PCI device "
+				 "(%04x:%02x:%02x.%01x)! "
+				 "perhaps already in-use?",
+				 domain, bus, slot, func);
+		goto out;
+	}
+
+	err = xen_pcibk_add_pci_dev(pdev, dev, devid,
+				    xen_pcibk_publish_pci_dev);
+	if (err)
+		goto out;
+
+	dev_dbg(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
+	if (xen_register_device_domain_owner(dev,
+					     pdev->xdev->otherend_id) != 0) {
+		dev_err(&dev->dev, "device has been assigned to another " \
+			"domain! Over-writting the ownership, but beware.\n");
+		xen_unregister_device_domain_owner(dev);
+		xen_register_device_domain_owner(dev, pdev->xdev->otherend_id);
+	}
+
+	/* TODO: It'd be nice to export a bridge and have all of its children
+	 * get exported with it. This may be best done in xend (which will
+	 * have to calculate resource usage anyway) but we probably want to
+	 * put something in here to ensure that if a bridge gets given to a
+	 * driver domain, that all devices under that bridge are not given
+	 * to other driver domains (as he who controls the bridge can disable
+	 * it and stop the other devices from working).
+	 */
+out:
+	return err;
+}
+
+static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
+				 int domain, int bus, int slot, int func)
+{
+	int err = 0;
+	struct pci_dev *dev;
+
+	dev_dbg(&pdev->xdev->dev, "removing dom %x bus %x slot %x func %x\n",
+		domain, bus, slot, func);
+
+	dev = xen_pcibk_get_pci_dev(pdev, domain, bus, PCI_DEVFN(slot, func));
+	if (!dev) {
+		err = -EINVAL;
+		dev_dbg(&pdev->xdev->dev, "Couldn't locate PCI device "
+			"(%04x:%02x:%02x.%01x)! not owned by this domain\n",
+			domain, bus, slot, func);
+		goto out;
+	}
+
+	dev_dbg(&dev->dev, "unregistering for %d\n", pdev->xdev->otherend_id);
+	xen_unregister_device_domain_owner(dev);
+
+	xen_pcibk_release_pci_dev(pdev, dev);
+
+out:
+	return err;
+}
+
+static int xen_pcibk_publish_pci_root(struct xen_pcibk_device *pdev,
+				    unsigned int domain, unsigned int bus)
+{
+	unsigned int d, b;
+	int i, root_num, len, err;
+	char str[64];
+
+	dev_dbg(&pdev->xdev->dev, "Publishing pci roots\n");
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+			   "root_num", "%d", &root_num);
+	if (err == 0 || err == -ENOENT)
+		root_num = 0;
+	else if (err < 0)
+		goto out;
+
+	/* Verify that we haven't already published this pci root */
+	for (i = 0; i < root_num; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+				   str, "%x:%x", &d, &b);
+		if (err < 0)
+			goto out;
+		if (err != 2) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (d == domain && b == bus) {
+			err = 0;
+			goto out;
+		}
+	}
+
+	len = snprintf(str, sizeof(str), "root-%d", root_num);
+	if (unlikely(len >= (sizeof(str) - 1))) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	dev_dbg(&pdev->xdev->dev, "writing root %d at %04x:%02x\n",
+		root_num, domain, bus);
+
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str,
+			    "%04x:%02x", domain, bus);
+	if (err)
+		goto out;
+
+	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename,
+			    "root_num", "%d", (root_num + 1));
+
+out:
+	return err;
+}
+
+static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev)
+{
+	int err = 0;
+	int num_devs;
+	int domain, bus, slot, func;
+	int substate;
+	int i, len;
+	char state_str[64];
+	char dev_str[64];
+
+
+	dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n");
+
+	/* Make sure we only reconfigure once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of devices");
+		goto out;
+	}
+
+	for (i = 0; i < num_devs; i++) {
+		len = snprintf(state_str, sizeof(state_str), "state-%d", i);
+		if (unlikely(len >= (sizeof(state_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, state_str,
+				   "%d", &substate);
+		if (err != 1)
+			substate = XenbusStateUnknown;
+
+		switch (substate) {
+		case XenbusStateInitialising:
+			dev_dbg(&pdev->xdev->dev, "Attaching dev-%d ...\n", i);
+
+			len = snprintf(dev_str, sizeof(dev_str), "dev-%d", i);
+			if (unlikely(len >= (sizeof(dev_str) - 1))) {
+				err = -ENOMEM;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "String overflow while "
+						 "reading configuration");
+				goto out;
+			}
+			err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+					   dev_str, "%x:%x:%x.%x",
+					   &domain, &bus, &slot, &func);
+			if (err < 0) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error reading device "
+						 "configuration");
+				goto out;
+			}
+			if (err != 4) {
+				err = -EINVAL;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error parsing pci device "
+						 "configuration");
+				goto out;
+			}
+
+			err = xen_pcibk_export_device(pdev, domain, bus, slot,
+						    func, i);
+			if (err)
+				goto out;
+
+			/* Publish pci roots. */
+			err = xen_pcibk_publish_pci_roots(pdev,
+						xen_pcibk_publish_pci_root);
+			if (err) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error while publish PCI root"
+						 "buses for frontend");
+				goto out;
+			}
+
+			err = xenbus_printf(XBT_NIL, pdev->xdev->nodename,
+					    state_str, "%d",
+					    XenbusStateInitialised);
+			if (err) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error switching substate of "
+						 "dev-%d\n", i);
+				goto out;
+			}
+			break;
+
+		case XenbusStateClosing:
+			dev_dbg(&pdev->xdev->dev, "Detaching dev-%d ...\n", i);
+
+			len = snprintf(dev_str, sizeof(dev_str), "vdev-%d", i);
+			if (unlikely(len >= (sizeof(dev_str) - 1))) {
+				err = -ENOMEM;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "String overflow while "
+						 "reading configuration");
+				goto out;
+			}
+			err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename,
+					   dev_str, "%x:%x:%x.%x",
+					   &domain, &bus, &slot, &func);
+			if (err < 0) {
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error reading device "
+						 "configuration");
+				goto out;
+			}
+			if (err != 4) {
+				err = -EINVAL;
+				xenbus_dev_fatal(pdev->xdev, err,
+						 "Error parsing pci device "
+						 "configuration");
+				goto out;
+			}
+
+			err = xen_pcibk_remove_device(pdev, domain, bus, slot,
+						    func);
+			if (err)
+				goto out;
+
+			/* TODO: If at some point we implement support for pci
+			 * root hot-remove on pcifront side, we'll need to
+			 * remove unnecessary xenstore nodes of pci roots here.
+			 */
+
+			break;
+
+		default:
+			break;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfigured);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to reconfigured state!");
+		goto out;
+	}
+
+out:
+	return 0;
+}
+
+static void xen_pcibk_frontend_changed(struct xenbus_device *xdev,
+				     enum xenbus_state fe_state)
+{
+	struct xen_pcibk_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	dev_dbg(&xdev->dev, "fe state changed %d\n", fe_state);
+
+	switch (fe_state) {
+	case XenbusStateInitialised:
+		xen_pcibk_attach(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		xen_pcibk_reconfigure(pdev);
+		break;
+
+	case XenbusStateConnected:
+		/* pcifront switched its state from reconfiguring to connected.
+		 * Then switch to connected state.
+		 */
+		xenbus_switch_state(xdev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+		xen_pcibk_disconnect(pdev);
+		xenbus_switch_state(xdev, XenbusStateClosing);
+		break;
+
+	case XenbusStateClosed:
+		xen_pcibk_disconnect(pdev);
+		xenbus_switch_state(xdev, XenbusStateClosed);
+		if (xenbus_dev_is_online(xdev))
+			break;
+		/* fall through if not online */
+	case XenbusStateUnknown:
+		dev_dbg(&xdev->dev, "frontend is gone! unregister device\n");
+		device_unregister(&xdev->dev);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev)
+{
+	/* Get configuration from xend (if available now) */
+	int domain, bus, slot, func;
+	int err = 0;
+	int i, num_devs;
+	char dev_str[64];
+	char state_str[64];
+
+	/* It's possible we could get the call to setup twice, so make sure
+	 * we're not already connected.
+	 */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitWait)
+		goto out;
+
+	dev_dbg(&pdev->xdev->dev, "getting be setup\n");
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of devices");
+		goto out;
+	}
+
+	for (i = 0; i < num_devs; i++) {
+		int l = snprintf(dev_str, sizeof(dev_str), "dev-%d", i);
+		if (unlikely(l >= (sizeof(dev_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, dev_str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err < 0) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading device configuration");
+			goto out;
+		}
+		if (err != 4) {
+			err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error parsing pci device "
+					 "configuration");
+			goto out;
+		}
+
+		err = xen_pcibk_export_device(pdev, domain, bus, slot, func, i);
+		if (err)
+			goto out;
+
+		/* Switch substate of this device. */
+		l = snprintf(state_str, sizeof(state_str), "state-%d", i);
+		if (unlikely(l >= (sizeof(state_str) - 1))) {
+			err = -ENOMEM;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "String overflow while reading "
+					 "configuration");
+			goto out;
+		}
+		err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, state_str,
+				    "%d", XenbusStateInitialised);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err, "Error switching "
+					 "substate of dev-%d\n", i);
+			goto out;
+		}
+	}
+
+	err = xen_pcibk_publish_pci_roots(pdev, xen_pcibk_publish_pci_root);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error while publish PCI root buses "
+				 "for frontend");
+		goto out;
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+	if (err)
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error switching to initialised state!");
+
+out:
+	if (!err)
+		/* see if pcifront is already configured (if not, we'll wait) */
+		xen_pcibk_attach(pdev);
+
+	return err;
+}
+
+static void xen_pcibk_be_watch(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len)
+{
+	struct xen_pcibk_device *pdev =
+	    container_of(watch, struct xen_pcibk_device, be_watch);
+
+	switch (xenbus_read_driver_state(pdev->xdev->nodename)) {
+	case XenbusStateInitWait:
+		xen_pcibk_setup_backend(pdev);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int xen_pcibk_xenbus_probe(struct xenbus_device *dev,
+				const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct xen_pcibk_device *pdev = alloc_pdev(dev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(dev, err,
+				 "Error allocating xen_pcibk_device struct");
+		goto out;
+	}
+
+	/* wait for xend to configure us */
+	err = xenbus_switch_state(dev, XenbusStateInitWait);
+	if (err)
+		goto out;
+
+	/* watch the backend node for backend configuration information */
+	err = xenbus_watch_path(dev, dev->nodename, &pdev->be_watch,
+				xen_pcibk_be_watch);
+	if (err)
+		goto out;
+
+	pdev->be_watching = 1;
+
+	/* We need to force a call to our callback here in case
+	 * xend already configured us!
+	 */
+	xen_pcibk_be_watch(&pdev->be_watch, NULL, 0);
+
+out:
+	return err;
+}
+
+static int xen_pcibk_xenbus_remove(struct xenbus_device *dev)
+{
+	struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev);
+
+	if (pdev != NULL)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_xen_pcibk_driver = {
+	.name			= DRV_NAME,
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= xen_pcibk_xenbus_probe,
+	.remove			= xen_pcibk_xenbus_remove,
+	.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");
+	if (!xen_pcibk_wq) {
+		printk(KERN_ERR "%s: create"
+			"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);
+}
+
+void __exit xen_pcibk_xenbus_unregister(void)
+{
+	destroy_workqueue(xen_pcibk_wq);
+	xenbus_unregister_driver(&xenbus_xen_pcibk_driver);
+}

drivers/xen/xen-selfballoon.c

@@ -0,0 +1,485 @@
+/******************************************************************************
+ * Xen selfballoon driver (and optional frontswap self-shrinking driver)
+ *
+ * Copyright (c) 2009-2011, Dan Magenheimer, Oracle Corp.
+ *
+ * This code complements the cleancache and frontswap patchsets to optimize
+ * support for Xen Transcendent Memory ("tmem").  The policy it implements
+ * is rudimentary and will likely improve over time, but it does work well
+ * enough today.
+ *
+ * Two functionalities are implemented here which both use "control theory"
+ * (feedback) to optimize memory utilization. In a virtualized environment
+ * such as Xen, RAM is often a scarce resource and we would like to ensure
+ * that each of a possibly large number of virtual machines is using RAM
+ * efficiently, i.e. using as little as possible when under light load
+ * and obtaining as much as possible when memory demands are high.
+ * Since RAM needs vary highly dynamically and sometimes dramatically,
+ * "hysteresis" is used, that is, memory target is determined not just
+ * on current data but also on past data stored in the system.
+ *
+ * "Selfballooning" creates memory pressure by managing the Xen balloon
+ * driver to decrease and increase available kernel memory, driven
+ * largely by the target value of "Committed_AS" (see /proc/meminfo).
+ * Since Committed_AS does not account for clean mapped pages (i.e. pages
+ * in RAM that are identical to pages on disk), selfballooning has the
+ * affect of pushing less frequently used clean pagecache pages out of
+ * kernel RAM and, presumably using cleancache, into Xen tmem where
+ * Xen can more efficiently optimize RAM utilization for such pages.
+ *
+ * When kernel memory demand unexpectedly increases faster than Xen, via
+ * the selfballoon driver, is able to (or chooses to) provide usable RAM,
+ * the kernel may invoke swapping.  In most cases, frontswap is able
+ * to absorb this swapping into Xen tmem.  However, due to the fact
+ * that the kernel swap subsystem assumes swapping occurs to a disk,
+ * swapped pages may sit on the disk for a very long time; even if
+ * the kernel knows the page will never be used again.  This is because
+ * the disk space costs very little and can be overwritten when
+ * necessary.  When such stale pages are in frontswap, however, they
+ * are taking up valuable real estate.  "Frontswap selfshrinking" works
+ * to resolve this:  When frontswap activity is otherwise stable
+ * and the guest kernel is not under memory pressure, the "frontswap
+ * selfshrinking" accounts for this by providing pressure to remove some
+ * pages from frontswap and return them to kernel memory.
+ *
+ * For both "selfballooning" and "frontswap-selfshrinking", a worker
+ * thread is used and sysfs tunables are provided to adjust the frequency
+ * and rate of adjustments to achieve the goal, as well as to disable one
+ * or both functions independently.
+ *
+ * While some argue that this functionality can and should be implemented
+ * in userspace, it has been observed that bad things happen (e.g. OOMs).
+ *
+ * System configuration note: Selfballooning should not be enabled on
+ * systems without a sufficiently large swap device configured; for best
+ * results, it is recommended that total swap be increased by the size
+ * of the guest memory.  Also, while technically not required to be
+ * configured, it is highly recommended that frontswap also be configured
+ * and enabled when selfballooning is running.  So, selfballooning
+ * is disabled by default if frontswap is not configured and can only
+ * be enabled with the "selfballooning" kernel boot option; similarly
+ * selfballooning is enabled by default if frontswap is configured and
+ * can be disabled with the "noselfballooning" kernel boot option.  Finally,
+ * when frontswap is configured, frontswap-selfshrinking can be disabled
+ * with the "noselfshrink" kernel boot option.
+ *
+ * Selfballooning is disallowed in domain0 and force-disabled.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+
+#include <xen/balloon.h>
+
+#include <xen/tmem.h>
+
+/* Enable/disable with sysfs. */
+static int xen_selfballooning_enabled __read_mostly;
+
+/*
+ * Controls rate at which memory target (this iteration) approaches
+ * ultimate goal when memory need is increasing (up-hysteresis) or
+ * decreasing (down-hysteresis). Higher values of hysteresis cause
+ * slower increases/decreases. The default values for the various
+ * parameters were deemed reasonable by experimentation, may be
+ * workload-dependent, and can all be adjusted via sysfs.
+ */
+static unsigned int selfballoon_downhysteresis __read_mostly = 8;
+static unsigned int selfballoon_uphysteresis __read_mostly = 1;
+
+/* In HZ, controls frequency of worker invocation. */
+static unsigned int selfballoon_interval __read_mostly = 5;
+
+static void selfballoon_process(struct work_struct *work);
+static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
+
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+
+/* Enable/disable with sysfs. */
+static bool frontswap_selfshrinking __read_mostly;
+
+/* Enable/disable with kernel boot option. */
+static bool use_frontswap_selfshrink __initdata = true;
+
+/*
+ * The default values for the following parameters were deemed reasonable
+ * by experimentation, may be workload-dependent, and can all be
+ * adjusted via sysfs.
+ */
+
+/* Control rate for frontswap shrinking. Higher hysteresis is slower. */
+static unsigned int frontswap_hysteresis __read_mostly = 20;
+
+/*
+ * Number of selfballoon worker invocations to wait before observing that
+ * frontswap selfshrinking should commence. Note that selfshrinking does
+ * not use a separate worker thread.
+ */
+static unsigned int frontswap_inertia __read_mostly = 3;
+
+/* Countdown to next invocation of frontswap_shrink() */
+static unsigned long frontswap_inertia_counter;
+
+/*
+ * Invoked by the selfballoon worker thread, uses current number of pages
+ * in frontswap (frontswap_curr_pages()), previous status, and control
+ * values (hysteresis and inertia) to determine if frontswap should be
+ * shrunk and what the new frontswap size should be.  Note that
+ * frontswap_shrink is essentially a partial swapoff that immediately
+ * transfers pages from the "swap device" (frontswap) back into kernel
+ * RAM; despite the name, frontswap "shrinking" is very different from
+ * the "shrinker" interface used by the kernel MM subsystem to reclaim
+ * memory.
+ */
+static void frontswap_selfshrink(void)
+{
+	static unsigned long cur_frontswap_pages;
+	static unsigned long last_frontswap_pages;
+	static unsigned long tgt_frontswap_pages;
+
+	last_frontswap_pages = cur_frontswap_pages;
+	cur_frontswap_pages = frontswap_curr_pages();
+	if (!cur_frontswap_pages ||
+			(cur_frontswap_pages > last_frontswap_pages)) {
+		frontswap_inertia_counter = frontswap_inertia;
+		return;
+	}
+	if (frontswap_inertia_counter && --frontswap_inertia_counter)
+		return;
+	if (cur_frontswap_pages <= frontswap_hysteresis)
+		tgt_frontswap_pages = 0;
+	else
+		tgt_frontswap_pages = cur_frontswap_pages -
+			(cur_frontswap_pages / frontswap_hysteresis);
+	frontswap_shrink(tgt_frontswap_pages);
+}
+
+static int __init xen_nofrontswap_selfshrink_setup(char *s)
+{
+	use_frontswap_selfshrink = false;
+	return 1;
+}
+
+__setup("noselfshrink", xen_nofrontswap_selfshrink_setup);
+
+/* Disable with kernel boot option. */
+static bool use_selfballooning __initdata = true;
+
+static int __init xen_noselfballooning_setup(char *s)
+{
+	use_selfballooning = false;
+	return 1;
+}
+
+__setup("noselfballooning", xen_noselfballooning_setup);
+#else /* !CONFIG_FRONTSWAP */
+/* Enable with kernel boot option. */
+static bool use_selfballooning __initdata = false;
+
+static int __init xen_selfballooning_setup(char *s)
+{
+	use_selfballooning = true;
+	return 1;
+}
+
+__setup("selfballooning", xen_selfballooning_setup);
+#endif /* CONFIG_FRONTSWAP */
+
+/*
+ * Use current balloon size, the goal (vm_committed_as), and hysteresis
+ * parameters to set a new target balloon size
+ */
+static void selfballoon_process(struct work_struct *work)
+{
+	unsigned long cur_pages, goal_pages, tgt_pages;
+	bool reset_timer = false;
+
+	if (xen_selfballooning_enabled) {
+		cur_pages = balloon_stats.current_pages;
+		tgt_pages = cur_pages; /* default is no change */
+		goal_pages = percpu_counter_read_positive(&vm_committed_as) +
+			balloon_stats.current_pages - totalram_pages;
+#ifdef CONFIG_FRONTSWAP
+		/* allow space for frontswap pages to be repatriated */
+		if (frontswap_selfshrinking && frontswap_enabled)
+			goal_pages += frontswap_curr_pages();
+#endif
+		if (cur_pages > goal_pages)
+			tgt_pages = cur_pages -
+				((cur_pages - goal_pages) /
+				  selfballoon_downhysteresis);
+		else if (cur_pages < goal_pages)
+			tgt_pages = cur_pages +
+				((goal_pages - cur_pages) /
+				  selfballoon_uphysteresis);
+		/* else if cur_pages == goal_pages, no change */
+		balloon_set_new_target(tgt_pages);
+		reset_timer = true;
+	}
+#ifdef CONFIG_FRONTSWAP
+	if (frontswap_selfshrinking && frontswap_enabled) {
+		frontswap_selfshrink();
+		reset_timer = true;
+	}
+#endif
+	if (reset_timer)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+}
+
+#ifdef CONFIG_SYSFS
+
+#include <linux/sysdev.h>
+#include <linux/capability.h>
+
+#define SELFBALLOON_SHOW(name, format, args...)				\
+	static ssize_t show_##name(struct sys_device *dev,	\
+					   struct sysdev_attribute *attr, \
+					   char *buf) \
+	{ \
+		return sprintf(buf, format, ##args); \
+	}
+
+SELFBALLOON_SHOW(selfballooning, "%d\n", xen_selfballooning_enabled);
+
+static ssize_t store_selfballooning(struct sys_device *dev,
+			    struct sysdev_attribute *attr,
+			    const char *buf,
+			    size_t count)
+{
+	bool was_enabled = xen_selfballooning_enabled;
+	unsigned long tmp;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = strict_strtoul(buf, 10, &tmp);
+	if (err || ((tmp != 0) && (tmp != 1)))
+		return -EINVAL;
+
+	xen_selfballooning_enabled = !!tmp;
+	if (!was_enabled && xen_selfballooning_enabled)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+
+	return count;
+}
+
+static SYSDEV_ATTR(selfballooning, S_IRUGO | S_IWUSR,
+		   show_selfballooning, store_selfballooning);
+
+SELFBALLOON_SHOW(selfballoon_interval, "%d\n", selfballoon_interval);
+
+static ssize_t store_selfballoon_interval(struct sys_device *dev,
+					  struct sysdev_attribute *attr,
+					  const char *buf,
+					  size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_interval = val;
+	return count;
+}
+
+static SYSDEV_ATTR(selfballoon_interval, S_IRUGO | S_IWUSR,
+		   show_selfballoon_interval, store_selfballoon_interval);
+
+SELFBALLOON_SHOW(selfballoon_downhys, "%d\n", selfballoon_downhysteresis);
+
+static ssize_t store_selfballoon_downhys(struct sys_device *dev,
+					 struct sysdev_attribute *attr,
+					 const char *buf,
+					 size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_downhysteresis = val;
+	return count;
+}
+
+static SYSDEV_ATTR(selfballoon_downhysteresis, S_IRUGO | S_IWUSR,
+		   show_selfballoon_downhys, store_selfballoon_downhys);
+
+
+SELFBALLOON_SHOW(selfballoon_uphys, "%d\n", selfballoon_uphysteresis);
+
+static ssize_t store_selfballoon_uphys(struct sys_device *dev,
+				       struct sysdev_attribute *attr,
+				       const char *buf,
+				       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_uphysteresis = val;
+	return count;
+}
+
+static SYSDEV_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
+		   show_selfballoon_uphys, store_selfballoon_uphys);
+
+#ifdef CONFIG_FRONTSWAP
+SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
+
+static ssize_t store_frontswap_selfshrinking(struct sys_device *dev,
+					     struct sysdev_attribute *attr,
+					     const char *buf,
+					     size_t count)
+{
+	bool was_enabled = frontswap_selfshrinking;
+	unsigned long tmp;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &tmp);
+	if (err || ((tmp != 0) && (tmp != 1)))
+		return -EINVAL;
+	frontswap_selfshrinking = !!tmp;
+	if (!was_enabled && !xen_selfballooning_enabled &&
+	     frontswap_selfshrinking)
+		schedule_delayed_work(&selfballoon_worker,
+			selfballoon_interval * HZ);
+
+	return count;
+}
+
+static SYSDEV_ATTR(frontswap_selfshrinking, S_IRUGO | S_IWUSR,
+		   show_frontswap_selfshrinking, store_frontswap_selfshrinking);
+
+SELFBALLOON_SHOW(frontswap_inertia, "%d\n", frontswap_inertia);
+
+static ssize_t store_frontswap_inertia(struct sys_device *dev,
+				       struct sysdev_attribute *attr,
+				       const char *buf,
+				       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	frontswap_inertia = val;
+	frontswap_inertia_counter = val;
+	return count;
+}
+
+static SYSDEV_ATTR(frontswap_inertia, S_IRUGO | S_IWUSR,
+		   show_frontswap_inertia, store_frontswap_inertia);
+
+SELFBALLOON_SHOW(frontswap_hysteresis, "%d\n", frontswap_hysteresis);
+
+static ssize_t store_frontswap_hysteresis(struct sys_device *dev,
+					  struct sysdev_attribute *attr,
+					  const char *buf,
+					  size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	frontswap_hysteresis = val;
+	return count;
+}
+
+static SYSDEV_ATTR(frontswap_hysteresis, S_IRUGO | S_IWUSR,
+		   show_frontswap_hysteresis, store_frontswap_hysteresis);
+
+#endif /* CONFIG_FRONTSWAP */
+
+static struct attribute *selfballoon_attrs[] = {
+	&attr_selfballooning.attr,
+	&attr_selfballoon_interval.attr,
+	&attr_selfballoon_downhysteresis.attr,
+	&attr_selfballoon_uphysteresis.attr,
+#ifdef CONFIG_FRONTSWAP
+	&attr_frontswap_selfshrinking.attr,
+	&attr_frontswap_hysteresis.attr,
+	&attr_frontswap_inertia.attr,
+#endif
+	NULL
+};
+
+static struct attribute_group selfballoon_group = {
+	.name = "selfballoon",
+	.attrs = selfballoon_attrs
+};
+#endif
+
+int register_xen_selfballooning(struct sys_device *sysdev)
+{
+	int error = -1;
+
+#ifdef CONFIG_SYSFS
+	error = sysfs_create_group(&sysdev->kobj, &selfballoon_group);
+#endif
+	return error;
+}
+EXPORT_SYMBOL(register_xen_selfballooning);
+
+static int __init xen_selfballoon_init(void)
+{
+	bool enable = false;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (xen_initial_domain()) {
+		pr_info("xen/balloon: Xen selfballooning driver "
+				"disabled for domain0.\n");
+		return -ENODEV;
+	}
+
+	xen_selfballooning_enabled = tmem_enabled && use_selfballooning;
+	if (xen_selfballooning_enabled) {
+		pr_info("xen/balloon: Initializing Xen "
+					"selfballooning driver.\n");
+		enable = true;
+	}
+#ifdef CONFIG_FRONTSWAP
+	frontswap_selfshrinking = tmem_enabled && use_frontswap_selfshrink;
+	if (frontswap_selfshrinking) {
+		pr_info("xen/balloon: Initializing frontswap "
+					"selfshrinking driver.\n");
+		enable = true;
+	}
+#endif
+	if (!enable)
+		return -ENODEV;
+
+	schedule_delayed_work(&selfballoon_worker, selfballoon_interval * HZ);
+
+	return 0;
+}
+
+subsys_initcall(xen_selfballoon_init);
+
+MODULE_LICENSE("GPL");

drivers/xen/xenbus/xenbus_probe.c

@@ -378,26 +378,32 @@ static void xenbus_dev_release(struct device *dev)
 		kfree(to_xenbus_device(dev));
 }
 
-static ssize_t xendev_show_nodename(struct device *dev,
-				    struct device_attribute *attr, char *buf)
+static ssize_t nodename_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->nodename);
 }
-static DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL);
 
-static ssize_t xendev_show_devtype(struct device *dev,
-				   struct device_attribute *attr, char *buf)
+static ssize_t devtype_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->devicetype);
 }
-static DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL);
 
-static ssize_t xendev_show_modalias(struct device *dev,
-				    struct device_attribute *attr, char *buf)
+static ssize_t modalias_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "xen:%s\n", to_xenbus_device(dev)->devicetype);
+	return sprintf(buf, "%s:%s\n", dev->bus->name,
+		       to_xenbus_device(dev)->devicetype);
 }
-static DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL);
+
+struct device_attribute xenbus_dev_attrs[] = {
+	__ATTR_RO(nodename),
+	__ATTR_RO(devtype),
+	__ATTR_RO(modalias),
+	__ATTR_NULL
+};
+EXPORT_SYMBOL_GPL(xenbus_dev_attrs);
 
 int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
@@ -449,25 +455,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 	if (err)
 		goto fail;
 
-	err = device_create_file(&xendev->dev, &dev_attr_nodename);
-	if (err)
-		goto fail_unregister;
-
-	err = device_create_file(&xendev->dev, &dev_attr_devtype);
-	if (err)
-		goto fail_remove_nodename;
-
-	err = device_create_file(&xendev->dev, &dev_attr_modalias);
-	if (err)
-		goto fail_remove_devtype;
-
 	return 0;
-fail_remove_devtype:
-	device_remove_file(&xendev->dev, &dev_attr_devtype);
-fail_remove_nodename:
-	device_remove_file(&xendev->dev, &dev_attr_nodename);
-fail_unregister:
-	device_unregister(&xendev->dev);
 fail:
 	kfree(xendev);
 	return err;

drivers/xen/xenbus/xenbus_probe.h

@@ -48,6 +48,8 @@ struct xen_bus_type
 	struct bus_type bus;
 };
 
+extern struct device_attribute xenbus_dev_attrs[];
+
 extern int xenbus_match(struct device *_dev, struct device_driver *_drv);
 extern int xenbus_dev_probe(struct device *_dev);
 extern int xenbus_dev_remove(struct device *_dev);

drivers/xen/xenbus/xenbus_probe_backend.c

@@ -107,6 +107,9 @@ static int xenbus_uevent_backend(struct device *dev,
 	if (xdev == NULL)
 		return -ENODEV;
 
+	if (add_uevent_var(env, "MODALIAS=xen-backend:%s", xdev->devicetype))
+		return -ENOMEM;
+
 	/* stuff we want to pass to /sbin/hotplug */
 	if (add_uevent_var(env, "XENBUS_TYPE=%s", xdev->devicetype))
 		return -ENOMEM;
@@ -183,10 +186,6 @@ static void frontend_changed(struct xenbus_watch *watch,
 	xenbus_otherend_changed(watch, vec, len, 0);
 }
 
-static struct device_attribute xenbus_backend_dev_attrs[] = {
-	__ATTR_NULL
-};
-
 static struct xen_bus_type xenbus_backend = {
 	.root = "backend",
 	.levels = 3,		/* backend/type/<frontend>/<id> */
@@ -200,7 +199,7 @@ static struct xen_bus_type xenbus_backend = {
 		.probe		= xenbus_dev_probe,
 		.remove		= xenbus_dev_remove,
 		.shutdown	= xenbus_dev_shutdown,
-		.dev_attrs	= xenbus_backend_dev_attrs,
+		.dev_attrs	= xenbus_dev_attrs,
 	},
 };
 

drivers/xen/xenbus/xenbus_probe_frontend.c

@@ -81,10 +81,6 @@ static void backend_changed(struct xenbus_watch *watch,
 	xenbus_otherend_changed(watch, vec, len, 1);
 }
 
-static struct device_attribute xenbus_frontend_dev_attrs[] = {
-	__ATTR_NULL
-};
-
 static const struct dev_pm_ops xenbus_pm_ops = {
 	.suspend	= xenbus_dev_suspend,
 	.resume		= xenbus_dev_resume,
@@ -106,7 +102,7 @@ static struct xen_bus_type xenbus_frontend = {
 		.probe		= xenbus_dev_probe,
 		.remove		= xenbus_dev_remove,
 		.shutdown	= xenbus_dev_shutdown,
-		.dev_attrs	= xenbus_frontend_dev_attrs,
+		.dev_attrs	= xenbus_dev_attrs,
 
 		.pm		= &xenbus_pm_ops,
 	},

include/xen/balloon.h

@@ -23,3 +23,13 @@ void balloon_set_new_target(unsigned long target);
 
 int alloc_xenballooned_pages(int nr_pages, struct page** pages);
 void free_xenballooned_pages(int nr_pages, struct page** pages);
+
+struct sys_device;
+#ifdef CONFIG_XEN_SELFBALLOONING
+extern int register_xen_selfballooning(struct sys_device *sysdev);
+#else
+static inline int register_xen_selfballooning(struct sys_device *sysdev)
+{
+	return -ENOSYS;
+}
+#endif

include/xen/hvc-console.h

@@ -6,11 +6,13 @@ extern struct console xenboot_console;
 #ifdef CONFIG_HVC_XEN
 void xen_console_resume(void);
 void xen_raw_console_write(const char *str);
+__attribute__((format(printf, 1, 2)))
 void xen_raw_printk(const char *fmt, ...);
 #else
 static inline void xen_console_resume(void) { }
 static inline void xen_raw_console_write(const char *str) { }
-static inline void xen_raw_printk(const char *fmt, ...) { }
+static inline __attribute__((format(printf, 1, 2)))
+void xen_raw_printk(const char *fmt, ...) { }
 #endif
 
 #endif	/* XEN_HVC_CONSOLE_H */

include/xen/interface/xen.h

@@ -450,6 +450,45 @@ struct start_info {
 	int8_t cmd_line[MAX_GUEST_CMDLINE];
 };
 
+struct dom0_vga_console_info {
+	uint8_t video_type;
+#define XEN_VGATYPE_TEXT_MODE_3 0x03
+#define XEN_VGATYPE_VESA_LFB    0x23
+
+	union {
+		struct {
+			/* Font height, in pixels. */
+			uint16_t font_height;
+			/* Cursor location (column, row). */
+			uint16_t cursor_x, cursor_y;
+			/* Number of rows and columns (dimensions in characters). */
+			uint16_t rows, columns;
+		} text_mode_3;
+
+		struct {
+			/* Width and height, in pixels. */
+			uint16_t width, height;
+			/* Bytes per scan line. */
+			uint16_t bytes_per_line;
+			/* Bits per pixel. */
+			uint16_t bits_per_pixel;
+			/* LFB physical address, and size (in units of 64kB). */
+			uint32_t lfb_base;
+			uint32_t lfb_size;
+			/* RGB mask offsets and sizes, as defined by VBE 1.2+ */
+			uint8_t  red_pos, red_size;
+			uint8_t  green_pos, green_size;
+			uint8_t  blue_pos, blue_size;
+			uint8_t  rsvd_pos, rsvd_size;
+
+			/* VESA capabilities (offset 0xa, VESA command 0x4f00). */
+			uint32_t gbl_caps;
+			/* Mode attributes (offset 0x0, VESA command 0x4f01). */
+			uint16_t mode_attrs;
+		} vesa_lfb;
+	} u;
+};
+
 /* These flags are passed in the 'flags' field of start_info_t. */
 #define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
 #define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */

include/xen/tmem.h

@@ -0,0 +1,5 @@
+#ifndef _XEN_TMEM_H
+#define _XEN_TMEM_H
+/* defined in drivers/xen/tmem.c */
+extern int tmem_enabled;
+#endif /* _XEN_TMEM_H */

include/xen/xenbus.h

@@ -223,7 +223,9 @@ int xenbus_free_evtchn(struct xenbus_device *dev, int port);
 
 enum xenbus_state xenbus_read_driver_state(const char *path);
 
+__attribute__((format(printf, 3, 4)))
 void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...);
+__attribute__((format(printf, 3, 4)))
 void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...);
 
 const char *xenbus_strstate(enum xenbus_state state);