Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:
	arch/sh/include/asm/Kbuild
	drivers/Makefile

Signed-off-by: Paul Mundt <lethal@linux-sh.org>

13 files changed, 1095 insertions, 85 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index fad3df2c127..60d71e9abe9 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -62,4 +62,18 @@ config XEN_SYS_HYPERVISOR
 	 virtual environment, /sys/hypervisor will still be present,
 	 but will have no xen contents.
 
+config XEN_PLATFORM_PCI
+	tristate "xen platform pci device driver"
+	depends on XEN_PVHVM
+	default m
+	help
+	  Driver for the Xen PCI Platform device: it is responsible for
+	  initializing xenbus and grant_table when running in a Xen HVM
+	  domain. As a consequence this driver is required to run any Xen PV
+	  frontend on Xen HVM.
+
+config SWIOTLB_XEN
+	def_bool y
+	depends on SWIOTLB
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 7c284342f30..fcaf838f54b 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -9,4 +9,6 @@ obj-$(CONFIG_XEN_XENCOMM)	+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)	+= balloon.o
 obj-$(CONFIG_XEN_DEV_EVTCHN)	+= evtchn.o
 obj-$(CONFIG_XENFS)		+= xenfs/
-obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
\ No newline at end of file
+obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
+obj-$(CONFIG_XEN_PLATFORM_PCI)	+= platform-pci.o
+obj-$(CONFIG_SWIOTLB_XEN)	+= swiotlb-xen.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 1a0d8c2a035..500290b150b 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -85,13 +85,6 @@ static struct sys_device balloon_sysdev;
 
 static int register_balloon(struct sys_device *sysdev);
 
-/*
- * Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and driver_pages, and
- * balloon lists.
- */
-static DEFINE_SPINLOCK(balloon_lock);
-
 static struct balloon_stats balloon_stats;
 
 /* We increase/decrease in batches which fit in a page */
@@ -210,7 +203,7 @@ static int increase_reservation(unsigned long nr_pages)
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	page = balloon_first_page();
 	for (i = 0; i < nr_pages; i++) {
@@ -254,7 +247,7 @@ static int increase_reservation(unsigned long nr_pages)
 	balloon_stats.current_pages += rc;
 
  out:
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return rc < 0 ? rc : rc != nr_pages;
 }
@@ -299,7 +292,7 @@ static int decrease_reservation(unsigned long nr_pages)
 	kmap_flush_unused();
 	flush_tlb_all();
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
@@ -315,7 +308,7 @@ static int decrease_reservation(unsigned long nr_pages)
 
 	balloon_stats.current_pages -= nr_pages;
 
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return need_sleep;
 }
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index db8f506817f..72f91bff29c 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -29,6 +29,7 @@
 #include <linux/bootmem.h>
 #include <linux/slab.h>
 
+#include <asm/desc.h>
 #include <asm/ptrace.h>
 #include <asm/irq.h>
 #include <asm/idle.h>
@@ -36,10 +37,14 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 
+#include <xen/xen.h>
+#include <xen/hvm.h>
 #include <xen/xen-ops.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.h>
+#include <xen/interface/hvm/hvm_op.h>
+#include <xen/interface/hvm/params.h>
 
 /*
  * This lock protects updates to the following mapping and reference-count
@@ -335,9 +340,18 @@ static int find_unbound_irq(void)
 	int irq;
 	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++)
+	for (irq = 0; irq < nr_irqs; irq++) {
+		desc = irq_to_desc(irq);
+		/* only 0->15 have init'd desc; handle irq > 16 */
+		if (desc == NULL)
+			break;
+		if (desc->chip == &no_irq_chip)
+			break;
+		if (desc->chip != &xen_dynamic_chip)
+			continue;
 		if (irq_info[irq].type == IRQT_UNBOUND)
 			break;
+	}
 
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
@@ -346,7 +360,7 @@ static int find_unbound_irq(void)
 	if (WARN_ON(desc == NULL))
 		return -1;
 
-	dynamic_irq_init(irq);
+	dynamic_irq_init_keep_chip_data(irq);
 
 	return irq;
 }
@@ -536,6 +550,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 	if (irq < 0)
 		return irq;
 
+	irqflags |= IRQF_NO_SUSPEND;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
 	if (retval != 0) {
 		unbind_from_irq(irq);
@@ -617,17 +632,13 @@ static DEFINE_PER_CPU(unsigned, xed_nesting_count);
  * a bitset of words which contain pending event bits.  The second
  * level is a bitset of pending events themselves.
  */
-void xen_evtchn_do_upcall(struct pt_regs *regs)
+static void __xen_evtchn_do_upcall(void)
 {
 	int cpu = get_cpu();
-	struct pt_regs *old_regs = set_irq_regs(regs);
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
  	unsigned count;
 
-	exit_idle();
-	irq_enter();
-
 	do {
 		unsigned long pending_words;
 
@@ -664,14 +675,31 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 		count = __get_cpu_var(xed_nesting_count);
 		__get_cpu_var(xed_nesting_count) = 0;
-	} while(count != 1);
+	} while (count != 1 || vcpu_info->evtchn_upcall_pending);
 
 out:
+
+	put_cpu();
+}
+
+void xen_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	exit_idle();
+	irq_enter();
+
+	__xen_evtchn_do_upcall();
+
 	irq_exit();
 	set_irq_regs(old_regs);
+}
 
-	put_cpu();
+void xen_hvm_evtchn_do_upcall(void)
+{
+	__xen_evtchn_do_upcall();
 }
+EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall);
 
 /* Rebind a new event channel to an existing irq. */
 void rebind_evtchn_irq(int evtchn, int irq)
@@ -708,7 +736,10 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	struct evtchn_bind_vcpu bind_vcpu;
 	int evtchn = evtchn_from_irq(irq);
 
-	if (!VALID_EVTCHN(evtchn))
+	/* events delivered via platform PCI interrupts are always
+	 * routed to vcpu 0 */
+	if (!VALID_EVTCHN(evtchn) ||
+		(xen_hvm_domain() && !xen_have_vector_callback))
 		return -1;
 
 	/* Send future instances of this interrupt to other vcpu. */
@@ -933,6 +964,44 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.retrigger	= retrigger_dynirq,
 };
 
+int xen_set_callback_via(uint64_t via)
+{
+	struct xen_hvm_param a;
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+	a.value = via;
+	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
+#ifdef CONFIG_XEN_PVHVM
+/* Vector callbacks are better than PCI interrupts to receive event
+ * channel notifications because we can receive vector callbacks on any
+ * vcpu and we don't need PCI support or APIC interactions. */
+void xen_callback_vector(void)
+{
+	int rc;
+	uint64_t callback_via;
+	if (xen_have_vector_callback) {
+		callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK);
+		rc = xen_set_callback_via(callback_via);
+		if (rc) {
+			printk(KERN_ERR "Request for Xen HVM callback vector"
+					" failed.\n");
+			xen_have_vector_callback = 0;
+			return;
+		}
+		printk(KERN_INFO "Xen HVM callback vector for event delivery is "
+				"enabled\n");
+		/* in the restore case the vector has already been allocated */
+		if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors))
+			alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector);
+	}
+}
+#else
+void xen_callback_vector(void) {}
+#endif
+
 void __init xen_init_IRQ(void)
 {
 	int i;
@@ -947,5 +1016,10 @@ void __init xen_init_IRQ(void)
 	for (i = 0; i < NR_EVENT_CHANNELS; i++)
 		mask_evtchn(i);
 
-	irq_ctx_init(smp_processor_id());
+	if (xen_hvm_domain()) {
+		xen_callback_vector();
+		native_init_IRQ();
+	} else {
+		irq_ctx_init(smp_processor_id());
+	}
 }
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index f66db3b91d6..6c453181649 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -37,11 +37,13 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <linux/io.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <xen/interface/memory.h>
 #include <asm/xen/hypercall.h>
 
 #include <asm/pgtable.h>
@@ -59,6 +61,8 @@ static unsigned int boot_max_nr_grant_frames;
 static int gnttab_free_count;
 static grant_ref_t gnttab_free_head;
 static DEFINE_SPINLOCK(gnttab_list_lock);
+unsigned long xen_hvm_resume_frames;
+EXPORT_SYMBOL_GPL(xen_hvm_resume_frames);
 
 static struct grant_entry *shared;
 
@@ -433,7 +437,7 @@ static unsigned int __max_nr_grant_frames(void)
 	return query.max_nr_frames;
 }
 
-static inline unsigned int max_nr_grant_frames(void)
+unsigned int gnttab_max_grant_frames(void)
 {
 	unsigned int xen_max = __max_nr_grant_frames();
 
@@ -441,6 +445,7 @@ static inline unsigned int max_nr_grant_frames(void)
 		return boot_max_nr_grant_frames;
 	return xen_max;
 }
+EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
 
 static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 {
@@ -449,6 +454,30 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 	unsigned int nr_gframes = end_idx + 1;
 	int rc;
 
+	if (xen_hvm_domain()) {
+		struct xen_add_to_physmap xatp;
+		unsigned int i = end_idx;
+		rc = 0;
+		/*
+		 * Loop backwards, so that the first hypercall has the largest
+		 * index, ensuring that the table will grow only once.
+		 */
+		do {
+			xatp.domid = DOMID_SELF;
+			xatp.idx = i;
+			xatp.space = XENMAPSPACE_grant_table;
+			xatp.gpfn = (xen_hvm_resume_frames >> PAGE_SHIFT) + i;
+			rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp);
+			if (rc != 0) {
+				printk(KERN_WARNING
+						"grant table add_to_physmap failed, err=%d\n", rc);
+				break;
+			}
+		} while (i-- > start_idx);
+
+		return rc;
+	}
+
 	frames = kmalloc(nr_gframes * sizeof(unsigned long), GFP_ATOMIC);
 	if (!frames)
 		return -ENOMEM;
@@ -465,7 +494,7 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 
 	BUG_ON(rc || setup.status);
 
-	rc = arch_gnttab_map_shared(frames, nr_gframes, max_nr_grant_frames(),
+	rc = arch_gnttab_map_shared(frames, nr_gframes, gnttab_max_grant_frames(),
 				    &shared);
 	BUG_ON(rc);
 
@@ -476,9 +505,27 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 
 int gnttab_resume(void)
 {
-	if (max_nr_grant_frames() < nr_grant_frames)
+	unsigned int max_nr_gframes;
+
+	max_nr_gframes = gnttab_max_grant_frames();
+	if (max_nr_gframes < nr_grant_frames)
 		return -ENOSYS;
-	return gnttab_map(0, nr_grant_frames - 1);
+
+	if (xen_pv_domain())
+		return gnttab_map(0, nr_grant_frames - 1);
+
+	if (!shared) {
+		shared = ioremap(xen_hvm_resume_frames, PAGE_SIZE * max_nr_gframes);
+		if (shared == NULL) {
+			printk(KERN_WARNING
+					"Failed to ioremap gnttab share frames!");
+			return -ENOMEM;
+		}
+	}
+
+	gnttab_map(0, nr_grant_frames - 1);
+
+	return 0;
 }
 
 int gnttab_suspend(void)
@@ -495,7 +542,7 @@ static int gnttab_expand(unsigned int req_entries)
 	cur = nr_grant_frames;
 	extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
 		 GREFS_PER_GRANT_FRAME);
-	if (cur + extra > max_nr_grant_frames())
+	if (cur + extra > gnttab_max_grant_frames())
 		return -ENOSPC;
 
 	rc = gnttab_map(cur, cur + extra - 1);
@@ -505,15 +552,12 @@ static int gnttab_expand(unsigned int req_entries)
 	return rc;
 }
 
-static int __devinit gnttab_init(void)
+int gnttab_init(void)
 {
 	int i;
 	unsigned int max_nr_glist_frames, nr_glist_frames;
 	unsigned int nr_init_grefs;
 
-	if (!xen_domain())
-		return -ENODEV;
-
 	nr_grant_frames = 1;
 	boot_max_nr_grant_frames = __max_nr_grant_frames();
 
@@ -556,5 +600,18 @@ static int __devinit gnttab_init(void)
 	kfree(gnttab_list);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(gnttab_init);
+
+static int __devinit __gnttab_init(void)
+{
+	/* Delay grant-table initialization in the PV on HVM case */
+	if (xen_hvm_domain())
+		return 0;
+
+	if (!xen_pv_domain())
+		return -ENODEV;
+
+	return gnttab_init();
+}
 
-core_initcall(gnttab_init);
+core_initcall(__gnttab_init);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 07e857b0de1..1799bd89031 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -9,6 +9,7 @@
 #include <linux/stop_machine.h>
 #include <linux/freezer.h>
 
+#include <xen/xen.h>
 #include <xen/xenbus.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
@@ -17,6 +18,7 @@
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
+#include <asm/xen/hypervisor.h>
 
 enum shutdown_state {
 	SHUTDOWN_INVALID = -1,
@@ -33,10 +35,30 @@ enum shutdown_state {
 static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
 
 #ifdef CONFIG_PM_SLEEP
-static int xen_suspend(void *data)
+static int xen_hvm_suspend(void *data)
 {
+	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
 	int *cancelled = data;
+
+	BUG_ON(!irqs_disabled());
+
+	*cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+
+	xen_hvm_post_suspend(*cancelled);
+	gnttab_resume();
+
+	if (!*cancelled) {
+		xen_irq_resume();
+		xen_timer_resume();
+	}
+
+	return 0;
+}
+
+static int xen_suspend(void *data)
+{
 	int err;
+	int *cancelled = data;
 
 	BUG_ON(!irqs_disabled());
 
@@ -106,7 +128,10 @@ static void do_suspend(void)
 		goto out_resume;
 	}
 
-	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
+	if (xen_hvm_domain())
+		err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0));
+	else
+		err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
 
 	dpm_resume_noirq(PMSG_RESUME);
 
@@ -255,7 +280,19 @@ static int shutdown_event(struct notifier_block *notifier,
 	return NOTIFY_DONE;
 }
 
-static int __init setup_shutdown_event(void)
+static int __init __setup_shutdown_event(void)
+{
+	/* Delay initialization in the PV on HVM case */
+	if (xen_hvm_domain())
+		return 0;
+
+	if (!xen_pv_domain())
+		return -ENODEV;
+
+	return xen_setup_shutdown_event();
+}
+
+int xen_setup_shutdown_event(void)
 {
 	static struct notifier_block xenstore_notifier = {
 		.notifier_call = shutdown_event
@@ -264,5 +301,6 @@ static int __init setup_shutdown_event(void)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
 
-subsys_initcall(setup_shutdown_event);
+subsys_initcall(__setup_shutdown_event);
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
new file mode 100644
index 00000000000..c01b5ddce52
--- /dev/null
+++ b/drivers/xen/platform-pci.c
@@ -0,0 +1,207 @@
+/******************************************************************************
+ * platform-pci.c
+ *
+ * Xen platform PCI device driver
+ * Copyright (c) 2005, Intel Corporation.
+ * Copyright (c) 2007, XenSource Inc.
+ * Copyright (c) 2010, Citrix
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <xen/platform_pci.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/hvm.h>
+#include <xen/xen-ops.h>
+
+#define DRV_NAME    "xen-platform-pci"
+
+MODULE_AUTHOR("ssmith@xensource.com and stefano.stabellini@eu.citrix.com");
+MODULE_DESCRIPTION("Xen platform PCI device");
+MODULE_LICENSE("GPL");
+
+static unsigned long platform_mmio;
+static unsigned long platform_mmio_alloc;
+static unsigned long platform_mmiolen;
+static uint64_t callback_via;
+
+unsigned long alloc_xen_mmio(unsigned long len)
+{
+	unsigned long addr;
+
+	addr = platform_mmio + platform_mmio_alloc;
+	platform_mmio_alloc += len;
+	BUG_ON(platform_mmio_alloc > platform_mmiolen);
+
+	return addr;
+}
+
+static uint64_t get_callback_via(struct pci_dev *pdev)
+{
+	u8 pin;
+	int irq;
+
+	irq = pdev->irq;
+	if (irq < 16)
+		return irq; /* ISA IRQ */
+
+	pin = pdev->pin;
+
+	/* We don't know the GSI. Specify the PCI INTx line instead. */
+	return ((uint64_t)0x01 << 56) | /* PCI INTx identifier */
+		((uint64_t)pci_domain_nr(pdev->bus) << 32) |
+		((uint64_t)pdev->bus->number << 16) |
+		((uint64_t)(pdev->devfn & 0xff) << 8) |
+		((uint64_t)(pin - 1) & 3);
+}
+
+static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id)
+{
+	xen_hvm_evtchn_do_upcall();
+	return IRQ_HANDLED;
+}
+
+static int xen_allocate_irq(struct pci_dev *pdev)
+{
+	return request_irq(pdev->irq, do_hvm_evtchn_intr,
+			IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
+			"xen-platform-pci", pdev);
+}
+
+static int platform_pci_resume(struct pci_dev *pdev)
+{
+	int err;
+	if (xen_have_vector_callback)
+		return 0;
+	err = xen_set_callback_via(callback_via);
+	if (err) {
+		dev_err(&pdev->dev, "platform_pci_resume failure!\n");
+		return err;
+	}
+	return 0;
+}
+
+static int __devinit platform_pci_init(struct pci_dev *pdev,
+				       const struct pci_device_id *ent)
+{
+	int i, ret;
+	long ioaddr, iolen;
+	long mmio_addr, mmio_len;
+	unsigned int max_nr_gframes;
+
+	i = pci_enable_device(pdev);
+	if (i)
+		return i;
+
+	ioaddr = pci_resource_start(pdev, 0);
+	iolen = pci_resource_len(pdev, 0);
+
+	mmio_addr = pci_resource_start(pdev, 1);
+	mmio_len = pci_resource_len(pdev, 1);
+
+	if (mmio_addr == 0 || ioaddr == 0) {
+		dev_err(&pdev->dev, "no resources found\n");
+		ret = -ENOENT;
+		goto pci_out;
+	}
+
+	if (request_mem_region(mmio_addr, mmio_len, DRV_NAME) == NULL) {
+		dev_err(&pdev->dev, "MEM I/O resource 0x%lx @ 0x%lx busy\n",
+		       mmio_addr, mmio_len);
+		ret = -EBUSY;
+		goto pci_out;
+	}
+
+	if (request_region(ioaddr, iolen, DRV_NAME) == NULL) {
+		dev_err(&pdev->dev, "I/O resource 0x%lx @ 0x%lx busy\n",
+		       iolen, ioaddr);
+		ret = -EBUSY;
+		goto mem_out;
+	}
+
+	platform_mmio = mmio_addr;
+	platform_mmiolen = mmio_len;
+
+	if (!xen_have_vector_callback) {
+		ret = xen_allocate_irq(pdev);
+		if (ret) {
+			dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
+			goto out;
+		}
+		callback_via = get_callback_via(pdev);
+		ret = xen_set_callback_via(callback_via);
+		if (ret) {
+			dev_warn(&pdev->dev, "Unable to set the evtchn callback "
+					 "err=%d\n", ret);
+			goto out;
+		}
+	}
+
+	max_nr_gframes = gnttab_max_grant_frames();
+	xen_hvm_resume_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes);
+	ret = gnttab_init();
+	if (ret)
+		goto out;
+	xenbus_probe(NULL);
+	ret = xen_setup_shutdown_event();
+	if (ret)
+		goto out;
+	return 0;
+
+out:
+	release_region(ioaddr, iolen);
+mem_out:
+	release_mem_region(mmio_addr, mmio_len);
+pci_out:
+	pci_disable_device(pdev);
+	return ret;
+}
+
+static struct pci_device_id platform_pci_tbl[] __devinitdata = {
+	{PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
+	{0,}
+};
+
+MODULE_DEVICE_TABLE(pci, platform_pci_tbl);
+
+static struct pci_driver platform_driver = {
+	.name =           DRV_NAME,
+	.probe =          platform_pci_init,
+	.id_table =       platform_pci_tbl,
+#ifdef CONFIG_PM
+	.resume_early =   platform_pci_resume,
+#endif
+};
+
+static int __init platform_pci_module_init(void)
+{
+	/* no unplug has been done, IGNORE hasn't been specified: just
+	 * return now */
+	if (!xen_platform_pci_unplug)
+		return -ENODEV;
+
+	return pci_register_driver(&platform_driver);
+}
+
+module_init(platform_pci_module_init);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
new file mode 100644
index 00000000000..54469c3eeac
--- /dev/null
+++ b/drivers/xen/swiotlb-xen.c
@@ -0,0 +1,515 @@
+/*
+ *  Copyright 2010
+ *  by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ *
+ * This code provides a IOMMU for Xen PV guests with PCI passthrough.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * PV guests under Xen are running in an non-contiguous memory architecture.
+ *
+ * When PCI pass-through is utilized, this necessitates an IOMMU for
+ * translating bus (DMA) to virtual and vice-versa and also providing a
+ * mechanism to have contiguous pages for device drivers operations (say DMA
+ * operations).
+ *
+ * Specifically, under Xen the Linux idea of pages is an illusion. It
+ * assumes that pages start at zero and go up to the available memory. To
+ * help with that, the Linux Xen MMU provides a lookup mechanism to
+ * translate the page frame numbers (PFN) to machine frame numbers (MFN)
+ * and vice-versa. The MFN are the "real" frame numbers. Furthermore
+ * memory is not contiguous. Xen hypervisor stitches memory for guests
+ * from different pools, which means there is no guarantee that PFN==MFN
+ * and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
+ * allocated in descending order (high to low), meaning the guest might
+ * never get any MFN's under the 4GB mark.
+ *
+ */
+
+#include <linux/bootmem.h>
+#include <linux/dma-mapping.h>
+#include <xen/swiotlb-xen.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+
+static char *xen_io_tlb_start, *xen_io_tlb_end;
+static unsigned long xen_io_tlb_nslabs;
+/*
+ * Quick lookup value of the bus address of the IOTLB.
+ */
+
+u64 start_dma_addr;
+
+static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+{
+	return phys_to_machine(XPADDR(paddr)).maddr;;
+}
+
+static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
+{
+	return machine_to_phys(XMADDR(baddr)).paddr;
+}
+
+static dma_addr_t xen_virt_to_bus(void *address)
+{
+	return xen_phys_to_bus(virt_to_phys(address));
+}
+
+static int check_pages_physically_contiguous(unsigned long pfn,
+					     unsigned int offset,
+					     size_t length)
+{
+	unsigned long next_mfn;
+	int i;
+	int nr_pages;
+
+	next_mfn = pfn_to_mfn(pfn);
+	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
+
+	for (i = 1; i < nr_pages; i++) {
+		if (pfn_to_mfn(++pfn) != ++next_mfn)
+			return 0;
+	}
+	return 1;
+}
+
+static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+{
+	unsigned long pfn = PFN_DOWN(p);
+	unsigned int offset = p & ~PAGE_MASK;
+
+	if (offset + size <= PAGE_SIZE)
+		return 0;
+	if (check_pages_physically_contiguous(pfn, offset, size))
+		return 0;
+	return 1;
+}
+
+static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
+{
+	unsigned long mfn = PFN_DOWN(dma_addr);
+	unsigned long pfn = mfn_to_local_pfn(mfn);
+	phys_addr_t paddr;
+
+	/* If the address is outside our domain, it CAN
+	 * have the same virtual address as another address
+	 * in our domain. Therefore _only_ check address within our domain.
+	 */
+	if (pfn_valid(pfn)) {
+		paddr = PFN_PHYS(pfn);
+		return paddr >= virt_to_phys(xen_io_tlb_start) &&
+		       paddr < virt_to_phys(xen_io_tlb_end);
+	}
+	return 0;
+}
+
+static int max_dma_bits = 32;
+
+static int
+xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+{
+	int i, rc;
+	int dma_bits;
+
+	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+
+	i = 0;
+	do {
+		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
+
+		do {
+			rc = xen_create_contiguous_region(
+				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				get_order(slabs << IO_TLB_SHIFT),
+				dma_bits);
+		} while (rc && dma_bits++ < max_dma_bits);
+		if (rc)
+			return rc;
+
+		i += slabs;
+	} while (i < nslabs);
+	return 0;
+}
+
+void __init xen_swiotlb_init(int verbose)
+{
+	unsigned long bytes;
+	int rc;
+
+	xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+	xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+
+	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from any location.
+	 */
+	xen_io_tlb_start = alloc_bootmem(bytes);
+	if (!xen_io_tlb_start)
+		panic("Cannot allocate SWIOTLB buffer");
+
+	xen_io_tlb_end = xen_io_tlb_start + bytes;
+	/*
+	 * And replace that memory with pages under 4GB.
+	 */
+	rc = xen_swiotlb_fixup(xen_io_tlb_start,
+			       bytes,
+			       xen_io_tlb_nslabs);
+	if (rc)
+		goto error;
+
+	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
+	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+
+	return;
+error:
+	panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\
+	      "We either don't have the permission or you do not have enough"\
+	      "free memory under 4GB!\n", rc);
+}
+
+void *
+xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags)
+{
+	void *ret;
+	int order = get_order(size);
+	u64 dma_mask = DMA_BIT_MASK(32);
+	unsigned long vstart;
+
+	/*
+	* Ignore region specifiers - the kernel's ideas of
+	* pseudo-phys memory layout has nothing to do with the
+	* machine physical layout.  We can't allocate highmem
+	* because we can't return a pointer to it.
+	*/
+	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
+		return ret;
+
+	vstart = __get_free_pages(flags, order);
+	ret = (void *)vstart;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
+
+	if (ret) {
+		if (xen_create_contiguous_region(vstart, order,
+						 fls64(dma_mask)) != 0) {
+			free_pages(vstart, order);
+			return NULL;
+		}
+		memset(ret, 0, size);
+		*dma_handle = virt_to_machine(ret).maddr;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
+
+void
+xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+			  dma_addr_t dev_addr)
+{
+	int order = get_order(size);
+
+	if (dma_release_from_coherent(hwdev, order, vaddr))
+		return;
+
+	xen_destroy_contiguous_region((unsigned long)vaddr, order);
+	free_pages((unsigned long)vaddr, order);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
+
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode.  The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dev_addr = xen_phys_to_bus(phys);
+	void *map;
+
+	BUG_ON(dir == DMA_NONE);
+	/*
+	 * If the address happens to be in the device's DMA window,
+	 * we can safely return the device addr and not worry about bounce
+	 * buffering it.
+	 */
+	if (dma_capable(dev, dev_addr, size) &&
+	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+		return dev_addr;
+
+	/*
+	 * Oh well, have to allocate and map a bounce buffer.
+	 */
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
+	if (!map)
+		return DMA_ERROR_CODE;
+
+	dev_addr = xen_virt_to_bus(map);
+
+	/*
+	 * Ensure that the address returned is DMA'ble
+	 */
+	if (!dma_capable(dev, dev_addr, size))
+		panic("map_single: bounce buffer is not DMA'ble");
+
+	return dev_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
+
+/*
+ * Unmap a single streaming mode DMA translation.  The dma_addr and size must
+ * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	xen_unmap_single(hwdev, dev_addr, size, dir);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so.  At the next point you give the dma
+ * address back to the card, you must first perform a
+ * xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			enum dma_sync_target target)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
+				       target);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
+
+void
+xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above xen_swiotlb_map_page
+ * interface.  Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length.  They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ *       DMA address/length pairs than there are SG table elements.
+ *       (for example via virtual mapping capabilities)
+ *       The routine returns the number of addr/length pairs actually
+ *       used, at most nents.
+ *
+ * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
+ * same here.
+ */
+int
+xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			 int nelems, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i) {
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
+
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length) ||
+		    range_straddles_page_boundary(paddr, sg->length)) {
+			void *map = swiotlb_tbl_map_single(hwdev,
+							   start_dma_addr,
+							   sg_phys(sg),
+							   sg->length, dir);
+			if (!map) {
+				/* Don't panic here, we expect map_sg users
+				   to do proper error handling. */
+				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+							   attrs);
+				sgl[0].dma_length = 0;
+				return DMA_ERROR_CODE;
+			}
+			sg->dma_address = xen_virt_to_bus(map);
+		} else
+			sg->dma_address = dev_addr;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
+
+int
+xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		   enum dma_data_direction dir)
+{
+	return xen_swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg);
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
+
+void
+xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		     enum dma_data_direction dir)
+{
+	return xen_swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg);
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+		    int nelems, enum dma_data_direction dir,
+		    enum dma_sync_target target)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_swiotlb_sync_single(hwdev, sg->dma_address,
+					sg->dma_length, dir, target);
+}
+
+void
+xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
+
+void
+xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			       int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
+
+int
+xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 7b3e973a1ae..7e49527189b 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -133,17 +133,12 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev,
 }
 EXPORT_SYMBOL_GPL(xenbus_watch_pathfmt);
 
+static void xenbus_switch_fatal(struct xenbus_device *, int, int,
+				const char *, ...);
 
-/**
- * xenbus_switch_state
- * @dev: xenbus device
- * @state: new state
- *
- * Advertise in the store a change of the given driver to the given new_state.
- * Return 0 on success, or -errno on error.  On error, the device will switch
- * to XenbusStateClosing, and the error will be saved in the store.
- */
-int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
+static int
+__xenbus_switch_state(struct xenbus_device *dev,
+		      enum xenbus_state state, int depth)
 {
 	/* We check whether the state is currently set to the given value, and
 	   if not, then the state is set.  We don't want to unconditionally
@@ -152,35 +147,65 @@ int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
 	   to it, as the device will be tearing down, and we don't want to
 	   resurrect that directory.
 
-	   Note that, because of this cached value of our state, this function
-	   will not work inside a Xenstore transaction (something it was
-	   trying to in the past) because dev->state would not get reset if
-	   the transaction was aborted.
-
+	   Note that, because of this cached value of our state, this
+	   function will not take a caller's Xenstore transaction
+	   (something it was trying to in the past) because dev->state
+	   would not get reset if the transaction was aborted.
 	 */
 
+	struct xenbus_transaction xbt;
 	int current_state;
-	int err;
+	int err, abort;
 
 	if (state == dev->state)
 		return 0;
 
-	err = xenbus_scanf(XBT_NIL, dev->nodename, "state", "%d",
-			   &current_state);
-	if (err != 1)
+again:
+	abort = 1;
+
+	err = xenbus_transaction_start(&xbt);
+	if (err) {
+		xenbus_switch_fatal(dev, depth, err, "starting transaction");
 		return 0;
+	}
+
+	err = xenbus_scanf(xbt, dev->nodename, "state", "%d", &current_state);
+	if (err != 1)
+		goto abort;
 
-	err = xenbus_printf(XBT_NIL, dev->nodename, "state", "%d", state);
+	err = xenbus_printf(xbt, dev->nodename, "state", "%d", state);
 	if (err) {
-		if (state != XenbusStateClosing) /* Avoid looping */
-			xenbus_dev_fatal(dev, err, "writing new state");
-		return err;
+		xenbus_switch_fatal(dev, depth, err, "writing new state");
+		goto abort;
 	}
 
-	dev->state = state;
+	abort = 0;
+abort:
+	err = xenbus_transaction_end(xbt, abort);
+	if (err) {
+		if (err == -EAGAIN && !abort)
+			goto again;
+		xenbus_switch_fatal(dev, depth, err, "ending transaction");
+	} else
+		dev->state = state;
 
 	return 0;
 }
+
+/**
+ * xenbus_switch_state
+ * @dev: xenbus device
+ * @state: new state
+ *
+ * Advertise in the store a change of the given driver to the given new_state.
+ * Return 0 on success, or -errno on error.  On error, the device will switch
+ * to XenbusStateClosing, and the error will be saved in the store.
+ */
+int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
+{
+	return __xenbus_switch_state(dev, state, 0);
+}
+
 EXPORT_SYMBOL_GPL(xenbus_switch_state);
 
 int xenbus_frontend_closed(struct xenbus_device *dev)
@@ -284,6 +309,23 @@ void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...)
 EXPORT_SYMBOL_GPL(xenbus_dev_fatal);
 
 /**
+ * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
+ * avoiding recursion within xenbus_switch_state.
+ */
+static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err,
+				const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	xenbus_va_dev_error(dev, err, fmt, ap);
+	va_end(ap);
+
+	if (!depth)
+		__xenbus_switch_state(dev, XenbusStateClosing, 1);
+}
+
+/**
  * xenbus_grant_ring
  * @dev: xenbus device
  * @ring_mfn: mfn of ring to grant
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 3479332113e..29bac511887 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -56,6 +56,9 @@
 #include <xen/events.h>
 #include <xen/page.h>
 
+#include <xen/platform_pci.h>
+#include <xen/hvm.h>
+
 #include "xenbus_comms.h"
 #include "xenbus_probe.h"
 
@@ -752,10 +755,7 @@ int register_xenstore_notifier(struct notifier_block *nb)
 {
 	int ret = 0;
 
-	if (xenstored_ready > 0)
-		ret = nb->notifier_call(nb, 0, NULL);
-	else
-		blocking_notifier_chain_register(&xenstore_chain, nb);
+	blocking_notifier_chain_register(&xenstore_chain, nb);
 
 	return ret;
 }
@@ -779,8 +779,23 @@ void xenbus_probe(struct work_struct *unused)
 	/* Notify others that xenstore is up */
 	blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
 }
+EXPORT_SYMBOL_GPL(xenbus_probe);
+
+static int __init xenbus_probe_initcall(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (xen_initial_domain() || xen_hvm_domain())
+		return 0;
+
+	xenbus_probe(NULL);
+	return 0;
+}
+
+device_initcall(xenbus_probe_initcall);
 
-static int __init xenbus_probe_init(void)
+static int __init xenbus_init(void)
 {
 	int err = 0;
 
@@ -805,11 +820,24 @@ static int __init xenbus_probe_init(void)
 	if (xen_initial_domain()) {
 		/* dom0 not yet supported */
 	} else {
+		if (xen_hvm_domain()) {
+			uint64_t v = 0;
+			err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+			if (err)
+				goto out_error;
+			xen_store_evtchn = (int)v;
+			err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
+			if (err)
+				goto out_error;
+			xen_store_mfn = (unsigned long)v;
+			xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
+		} else {
+			xen_store_evtchn = xen_start_info->store_evtchn;
+			xen_store_mfn = xen_start_info->store_mfn;
+			xen_store_interface = mfn_to_virt(xen_store_mfn);
+		}
 		xenstored_ready = 1;
-		xen_store_evtchn = xen_start_info->store_evtchn;
-		xen_store_mfn = xen_start_info->store_mfn;
 	}
-	xen_store_interface = mfn_to_virt(xen_store_mfn);
 
 	/* Initialize the interface to xenstore. */
 	err = xs_init();
@@ -819,9 +847,6 @@ static int __init xenbus_probe_init(void)
 		goto out_unreg_back;
 	}
 
-	if (!xen_initial_domain())
-		xenbus_probe(NULL);
-
 #ifdef CONFIG_XEN_COMPAT_XENFS
 	/*
 	 * Create xenfs mountpoint in /proc for compatibility with
@@ -842,7 +867,7 @@ static int __init xenbus_probe_init(void)
 	return err;
 }
 
-postcore_initcall(xenbus_probe_init);
+postcore_initcall(xenbus_init);
 
 MODULE_LICENSE("GPL");
 
@@ -950,6 +975,9 @@ static void wait_for_devices(struct xenbus_driver *xendrv)
 #ifndef MODULE
 static int __init boot_wait_for_devices(void)
 {
+	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+		return -ENODEV;
+
 	ready_to_wait_for_devices = 1;
 	wait_for_devices(NULL);
 	return 0;
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 7b547f53f65..5534690075a 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -76,6 +76,14 @@ struct xs_handle {
 	/*
 	 * Mutex ordering: transaction_mutex -> watch_mutex -> request_mutex.
 	 * response_mutex is never taken simultaneously with the other three.
+	 *
+	 * transaction_mutex must be held before incrementing
+	 * transaction_count. The mutex is held when a suspend is in
+	 * progress to prevent new transactions starting.
+	 *
+	 * When decrementing transaction_count to zero the wait queue
+	 * should be woken up, the suspend code waits for count to
+	 * reach zero.
 	 */
 
 	/* One request at a time. */
@@ -85,7 +93,9 @@ struct xs_handle {
 	struct mutex response_mutex;
 
 	/* Protect transactions against save/restore. */
-	struct rw_semaphore transaction_mutex;
+	struct mutex transaction_mutex;
+	atomic_t transaction_count;
+	wait_queue_head_t transaction_wq;
 
 	/* Protect watch (de)register against save/restore. */
 	struct rw_semaphore watch_mutex;
@@ -157,6 +167,31 @@ static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
 	return body;
 }
 
+static void transaction_start(void)
+{
+	mutex_lock(&xs_state.transaction_mutex);
+	atomic_inc(&xs_state.transaction_count);
+	mutex_unlock(&xs_state.transaction_mutex);
+}
+
+static void transaction_end(void)
+{
+	if (atomic_dec_and_test(&xs_state.transaction_count))
+		wake_up(&xs_state.transaction_wq);
+}
+
+static void transaction_suspend(void)
+{
+	mutex_lock(&xs_state.transaction_mutex);
+	wait_event(xs_state.transaction_wq,
+		   atomic_read(&xs_state.transaction_count) == 0);
+}
+
+static void transaction_resume(void)
+{
+	mutex_unlock(&xs_state.transaction_mutex);
+}
+
 void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 {
 	void *ret;
@@ -164,7 +199,7 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 	int err;
 
 	if (req_msg.type == XS_TRANSACTION_START)
-		down_read(&xs_state.transaction_mutex);
+		transaction_start();
 
 	mutex_lock(&xs_state.request_mutex);
 
@@ -180,7 +215,7 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 	if ((msg->type == XS_TRANSACTION_END) ||
 	    ((req_msg.type == XS_TRANSACTION_START) &&
 	     (msg->type == XS_ERROR)))
-		up_read(&xs_state.transaction_mutex);
+		transaction_end();
 
 	return ret;
 }
@@ -432,11 +467,11 @@ int xenbus_transaction_start(struct xenbus_transaction *t)
 {
 	char *id_str;
 
-	down_read(&xs_state.transaction_mutex);
+	transaction_start();
 
 	id_str = xs_single(XBT_NIL, XS_TRANSACTION_START, "", NULL);
 	if (IS_ERR(id_str)) {
-		up_read(&xs_state.transaction_mutex);
+		transaction_end();
 		return PTR_ERR(id_str);
 	}
 
@@ -461,7 +496,7 @@ int xenbus_transaction_end(struct xenbus_transaction t, int abort)
 
 	err = xs_error(xs_single(t, XS_TRANSACTION_END, abortstr, NULL));
 
-	up_read(&xs_state.transaction_mutex);
+	transaction_end();
 
 	return err;
 }
@@ -662,7 +697,7 @@ EXPORT_SYMBOL_GPL(unregister_xenbus_watch);
 
 void xs_suspend(void)
 {
-	down_write(&xs_state.transaction_mutex);
+	transaction_suspend();
 	down_write(&xs_state.watch_mutex);
 	mutex_lock(&xs_state.request_mutex);
 	mutex_lock(&xs_state.response_mutex);
@@ -677,7 +712,7 @@ void xs_resume(void)
 
 	mutex_unlock(&xs_state.response_mutex);
 	mutex_unlock(&xs_state.request_mutex);
-	up_write(&xs_state.transaction_mutex);
+	transaction_resume();
 
 	/* No need for watches_lock: the watch_mutex is sufficient. */
 	list_for_each_entry(watch, &watches, list) {
@@ -693,7 +728,7 @@ void xs_suspend_cancel(void)
 	mutex_unlock(&xs_state.response_mutex);
 	mutex_unlock(&xs_state.request_mutex);
 	up_write(&xs_state.watch_mutex);
-	up_write(&xs_state.transaction_mutex);
+	mutex_unlock(&xs_state.transaction_mutex);
 }
 
 static int xenwatch_thread(void *unused)
@@ -843,8 +878,10 @@ int xs_init(void)
 
 	mutex_init(&xs_state.request_mutex);
 	mutex_init(&xs_state.response_mutex);
-	init_rwsem(&xs_state.transaction_mutex);
+	mutex_init(&xs_state.transaction_mutex);
 	init_rwsem(&xs_state.watch_mutex);
+	atomic_set(&xs_state.transaction_count, 0);
+	init_waitqueue_head(&xs_state.transaction_wq);
 
 	/* Initialize the shared memory rings to talk to xenstored */
 	err = xb_init_comms();
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 8924d93136f..78bfab0700b 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -65,7 +65,7 @@ static struct file_system_type xenfs_type = {
 
 static int __init xenfs_init(void)
 {
-	if (xen_pv_domain())
+	if (xen_domain())
 		return register_filesystem(&xenfs_type);
 
 	printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n");
@@ -74,7 +74,7 @@ static int __init xenfs_init(void)
 
 static void __exit xenfs_exit(void)
 {
-	if (xen_pv_domain())
+	if (xen_domain())
 		unregister_filesystem(&xenfs_type);
 }
 
diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c
index f28ece39736..3b39c3752e2 100644
--- a/drivers/xen/xenfs/xenbus.c
+++ b/drivers/xen/xenfs/xenbus.c
@@ -124,6 +124,9 @@ static ssize_t xenbus_file_read(struct file *filp,
 	mutex_lock(&u->reply_mutex);
 	while (list_empty(&u->read_buffers)) {
 		mutex_unlock(&u->reply_mutex);
+		if (filp->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
 		ret = wait_event_interruptible(u->read_waitq,
 					       !list_empty(&u->read_buffers));
 		if (ret)