11 files changed, 808 insertions, 142 deletions

diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index dbfd56446c3..94c0c74434e 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -91,4 +91,16 @@ config TCG_ST33_I2C
         To compile this driver as a module, choose M here; the module will be
         called tpm_stm_st33_i2c.
 
+config TCG_XEN
+	tristate "XEN TPM Interface"
+	depends on TCG_TPM && XEN
+	select XEN_XENBUS_FRONTEND
+	---help---
+	  If you want to make TPM support available to a Xen user domain,
+	  say Yes and it will be accessible from within Linux. See
+	  the manpages for xl, xl.conf, and docs/misc/vtpm.txt in
+	  the Xen source repository for more details.
+	  To compile this driver as a module, choose M here; the module
+	  will be called xen-tpmfront.
+
 endif # TCG_TPM
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index a3736c97c65..eb41ff97d0a 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_TCG_ATMEL) += tpm_atmel.o
 obj-$(CONFIG_TCG_INFINEON) += tpm_infineon.o
 obj-$(CONFIG_TCG_IBMVTPM) += tpm_ibmvtpm.o
 obj-$(CONFIG_TCG_ST33_I2C) += tpm_i2c_stm_st33.o
+obj-$(CONFIG_TCG_XEN) += xen-tpmfront.o
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
new file mode 100644
index 00000000000..7a7929ba265
--- /dev/null
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -0,0 +1,473 @@
+/*
+ * Implementation of the Xen vTPM device frontend
+ *
+ * Author:  Daniel De Graaf <dgdegra@tycho.nsa.gov>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <xen/events.h>
+#include <xen/interface/io/tpmif.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/page.h>
+#include "tpm.h"
+
+struct tpm_private {
+	struct tpm_chip *chip;
+	struct xenbus_device *dev;
+
+	struct vtpm_shared_page *shr;
+
+	unsigned int evtchn;
+	int ring_ref;
+	domid_t backend_id;
+};
+
+enum status_bits {
+	VTPM_STATUS_RUNNING  = 0x1,
+	VTPM_STATUS_IDLE     = 0x2,
+	VTPM_STATUS_RESULT   = 0x4,
+	VTPM_STATUS_CANCELED = 0x8,
+};
+
+static u8 vtpm_status(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_CANCELED;
+	case VTPM_STATE_FINISH:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_RESULT;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL: /* cancel requested, not yet canceled */
+		return VTPM_STATUS_RUNNING;
+	default:
+		return 0;
+	}
+}
+
+static bool vtpm_req_canceled(struct tpm_chip *chip, u8 status)
+{
+	return status & VTPM_STATUS_CANCELED;
+}
+
+static void vtpm_cancel(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	priv->shr->state = VTPM_STATE_CANCEL;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+}
+
+static unsigned int shr_data_offset(struct vtpm_shared_page *shr)
+{
+	return sizeof(*shr) + sizeof(u32) * shr->nr_extra_pages;
+}
+
+static int vtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+
+	u32 ordinal;
+	unsigned long duration;
+
+	if (offset > PAGE_SIZE)
+		return -EINVAL;
+
+	if (offset + count > PAGE_SIZE)
+		return -EINVAL;
+
+	/* Wait for completion of any existing command or cancellation */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	memcpy(offset + (u8 *)shr, buf, count);
+	shr->length = count;
+	barrier();
+	shr->state = VTPM_STATE_SUBMIT;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+
+	ordinal = be32_to_cpu(((struct tpm_input_header*)buf)->ordinal);
+	duration = tpm_calc_ordinal_duration(chip, ordinal);
+
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, duration,
+			&chip->vendor.read_queue, true) < 0) {
+		/* got a signal or timeout, try to cancel */
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	return count;
+}
+
+static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+	size_t length = shr->length;
+
+	if (shr->state == VTPM_STATE_IDLE)
+		return -ECANCELED;
+
+	/* In theory the wait at the end of _send makes this one unnecessary */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_RESULT, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	if (offset > PAGE_SIZE)
+		return -EIO;
+
+	if (offset + length > PAGE_SIZE)
+		length = PAGE_SIZE - offset;
+
+	if (length > count)
+		length = count;
+
+	memcpy(buf, offset + (u8 *)shr, length);
+
+	return length;
+}
+
+ssize_t tpm_show_locality(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	u8 locality = priv->shr->locality;
+
+	return sprintf(buf, "%d\n", locality);
+}
+
+ssize_t tpm_store_locality(struct device *dev, struct device_attribute *attr,
+			const char *buf, size_t len)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	u8 val;
+
+	int rv = kstrtou8(buf, 0, &val);
+	if (rv)
+		return rv;
+
+	priv->shr->locality = val;
+
+	return len;
+}
+
+static const struct file_operations vtpm_ops = {
+	.owner = THIS_MODULE,
+	.llseek = no_llseek,
+	.open = tpm_open,
+	.read = tpm_read,
+	.write = tpm_write,
+	.release = tpm_release,
+};
+
+static DEVICE_ATTR(pubek, S_IRUGO, tpm_show_pubek, NULL);
+static DEVICE_ATTR(pcrs, S_IRUGO, tpm_show_pcrs, NULL);
+static DEVICE_ATTR(enabled, S_IRUGO, tpm_show_enabled, NULL);
+static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
+static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
+static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated,
+		NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
+static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
+static DEVICE_ATTR(locality, S_IRUGO | S_IWUSR, tpm_show_locality,
+		tpm_store_locality);
+
+static struct attribute *vtpm_attrs[] = {
+	&dev_attr_pubek.attr,
+	&dev_attr_pcrs.attr,
+	&dev_attr_enabled.attr,
+	&dev_attr_active.attr,
+	&dev_attr_owned.attr,
+	&dev_attr_temp_deactivated.attr,
+	&dev_attr_caps.attr,
+	&dev_attr_cancel.attr,
+	&dev_attr_durations.attr,
+	&dev_attr_timeouts.attr,
+	&dev_attr_locality.attr,
+	NULL,
+};
+
+static struct attribute_group vtpm_attr_grp = {
+	.attrs = vtpm_attrs,
+};
+
+#define TPM_LONG_TIMEOUT   (10 * 60 * HZ)
+
+static const struct tpm_vendor_specific tpm_vtpm = {
+	.status = vtpm_status,
+	.recv = vtpm_recv,
+	.send = vtpm_send,
+	.cancel = vtpm_cancel,
+	.req_complete_mask = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_complete_val  = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_canceled      = vtpm_req_canceled,
+	.attr_group = &vtpm_attr_grp,
+	.miscdev = {
+		.fops = &vtpm_ops,
+	},
+	.duration = {
+		TPM_LONG_TIMEOUT,
+		TPM_LONG_TIMEOUT,
+		TPM_LONG_TIMEOUT,
+	},
+};
+
+static irqreturn_t tpmif_interrupt(int dummy, void *dev_id)
+{
+	struct tpm_private *priv = dev_id;
+
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+	case VTPM_STATE_FINISH:
+		wake_up_interruptible(&priv->chip->vendor.read_queue);
+		break;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL:
+	default:
+		break;
+	}
+	return IRQ_HANDLED;
+}
+
+static int setup_chip(struct device *dev, struct tpm_private *priv)
+{
+	struct tpm_chip *chip;
+
+	chip = tpm_register_hardware(dev, &tpm_vtpm);
+	if (!chip)
+		return -ENODEV;
+
+	init_waitqueue_head(&chip->vendor.read_queue);
+
+	priv->chip = chip;
+	TPM_VPRIV(chip) = priv;
+
+	return 0;
+}
+
+/* caller must clean up in case of errors */
+static int setup_ring(struct xenbus_device *dev, struct tpm_private *priv)
+{
+	struct xenbus_transaction xbt;
+	const char *message = NULL;
+	int rv;
+
+	priv->shr = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!priv->shr) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
+		return -ENOMEM;
+	}
+
+	rv = xenbus_grant_ring(dev, virt_to_mfn(priv->shr));
+	if (rv < 0)
+		return rv;
+
+	priv->ring_ref = rv;
+
+	rv = xenbus_alloc_evtchn(dev, &priv->evtchn);
+	if (rv)
+		return rv;
+
+	rv = bind_evtchn_to_irqhandler(priv->evtchn, tpmif_interrupt, 0,
+				       "tpmif", priv);
+	if (rv <= 0) {
+		xenbus_dev_fatal(dev, rv, "allocating TPM irq");
+		return rv;
+	}
+	priv->chip->vendor.irq = rv;
+
+ again:
+	rv = xenbus_transaction_start(&xbt);
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "starting transaction");
+		return rv;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename,
+			"ring-ref", "%u", priv->ring_ref);
+	if (rv) {
+		message = "writing ring-ref";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "event-channel", "%u",
+			priv->evtchn);
+	if (rv) {
+		message = "writing event-channel";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "feature-protocol-v2", "1");
+	if (rv) {
+		message = "writing feature-protocol-v2";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_transaction_end(xbt, 0);
+	if (rv == -EAGAIN)
+		goto again;
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "completing transaction");
+		return rv;
+	}
+
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+ abort_transaction:
+	xenbus_transaction_end(xbt, 1);
+	if (message)
+		xenbus_dev_error(dev, rv, "%s", message);
+
+	return rv;
+}
+
+static void ring_free(struct tpm_private *priv)
+{
+	if (!priv)
+		return;
+
+	if (priv->ring_ref)
+		gnttab_end_foreign_access(priv->ring_ref, 0,
+				(unsigned long)priv->shr);
+	else
+		free_page((unsigned long)priv->shr);
+
+	if (priv->chip && priv->chip->vendor.irq)
+		unbind_from_irqhandler(priv->chip->vendor.irq, priv);
+
+	kfree(priv);
+}
+
+static int tpmfront_probe(struct xenbus_device *dev,
+		const struct xenbus_device_id *id)
+{
+	struct tpm_private *priv;
+	int rv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating priv structure");
+		return -ENOMEM;
+	}
+
+	rv = setup_chip(&dev->dev, priv);
+	if (rv) {
+		kfree(priv);
+		return rv;
+	}
+
+	rv = setup_ring(dev, priv);
+	if (rv) {
+		tpm_remove_hardware(&dev->dev);
+		ring_free(priv);
+		return rv;
+	}
+
+	tpm_get_timeouts(priv->chip);
+
+	dev_set_drvdata(&dev->dev, priv->chip);
+
+	return rv;
+}
+
+static int tpmfront_remove(struct xenbus_device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	tpm_remove_hardware(&dev->dev);
+	ring_free(priv);
+	TPM_VPRIV(chip) = NULL;
+	return 0;
+}
+
+static int tpmfront_resume(struct xenbus_device *dev)
+{
+	/* A suspend/resume/migrate will interrupt a vTPM anyway */
+	tpmfront_remove(dev);
+	return tpmfront_probe(dev, NULL);
+}
+
+static void backend_changed(struct xenbus_device *dev,
+		enum xenbus_state backend_state)
+{
+	int val;
+
+	switch (backend_state) {
+	case XenbusStateInitialised:
+	case XenbusStateConnected:
+		if (dev->state == XenbusStateConnected)
+			break;
+
+		if (xenbus_scanf(XBT_NIL, dev->otherend,
+				"feature-protocol-v2", "%d", &val) < 0)
+			val = 0;
+		if (!val) {
+			xenbus_dev_fatal(dev, -EINVAL,
+					"vTPM protocol 2 required");
+			return;
+		}
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+	case XenbusStateClosed:
+		device_unregister(&dev->dev);
+		xenbus_frontend_closed(dev);
+		break;
+	default:
+		break;
+	}
+}
+
+static const struct xenbus_device_id tpmfront_ids[] = {
+	{ "vtpm" },
+	{ "" }
+};
+MODULE_ALIAS("xen:vtpm");
+
+static DEFINE_XENBUS_DRIVER(tpmfront, ,
+		.probe = tpmfront_probe,
+		.remove = tpmfront_remove,
+		.resume = tpmfront_resume,
+		.otherend_changed = backend_changed,
+	);
+
+static int __init xen_tpmfront_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	return xenbus_register_frontend(&tpmfront_driver);
+}
+module_init(xen_tpmfront_init);
+
+static void __exit xen_tpmfront_exit(void)
+{
+	xenbus_unregister_driver(&tpmfront_driver);
+}
+module_exit(xen_tpmfront_exit);
+
+MODULE_AUTHOR("Daniel De Graaf <dgdegra@tycho.nsa.gov>");
+MODULE_DESCRIPTION("Xen vTPM Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 2a2ef97697b..3101cf6daf5 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -38,6 +38,7 @@
 
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
@@ -52,6 +53,7 @@
 #include <linux/notifier.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/percpu-defs.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -90,6 +92,8 @@ EXPORT_SYMBOL_GPL(balloon_stats);
 
 /* We increase/decrease in batches which fit in a page */
 static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)];
+static DEFINE_PER_CPU(struct page *, balloon_scratch_page);
+
 
 /* List of ballooned pages, threaded through the mem_map array. */
 static LIST_HEAD(ballooned_pages);
@@ -412,7 +416,8 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 		if (xen_pv_domain() && !PageHighMem(page)) {
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
-				__pte_ma(0), 0);
+				pfn_pte(page_to_pfn(__get_cpu_var(balloon_scratch_page)),
+					PAGE_KERNEL_RO), 0);
 			BUG_ON(ret);
 		}
 #endif
@@ -425,7 +430,13 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
 		pfn = mfn_to_pfn(frame_list[i]);
-		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			unsigned long p;
+			struct page *pg;
+			pg = __get_cpu_var(balloon_scratch_page);
+			p = page_to_pfn(pg);
+			__set_phys_to_machine(pfn, pfn_to_mfn(p));
+		}
 		balloon_append(pfn_to_page(pfn));
 	}
 
@@ -480,6 +491,18 @@ static void balloon_process(struct work_struct *work)
 	mutex_unlock(&balloon_mutex);
 }
 
+struct page *get_balloon_scratch_page(void)
+{
+	struct page *ret = get_cpu_var(balloon_scratch_page);
+	BUG_ON(ret == NULL);
+	return ret;
+}
+
+void put_balloon_scratch_page(void)
+{
+	put_cpu_var(balloon_scratch_page);
+}
+
 /* Resets the Xen limit, sets new target, and kicks off processing. */
 void balloon_set_new_target(unsigned long target)
 {
@@ -573,13 +596,47 @@ static void __init balloon_add_region(unsigned long start_pfn,
 	}
 }
 
+static int __cpuinit balloon_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	switch (action) {
+	case CPU_UP_PREPARE:
+		if (per_cpu(balloon_scratch_page, cpu) != NULL)
+			break;
+		per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
+		if (per_cpu(balloon_scratch_page, cpu) == NULL) {
+			pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
+			return NOTIFY_BAD;
+		}
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block balloon_cpu_notifier __cpuinitdata = {
+	.notifier_call	= balloon_cpu_notify,
+};
+
 static int __init balloon_init(void)
 {
-	int i;
+	int i, cpu;
 
 	if (!xen_domain())
 		return -ENODEV;
 
+	for_each_online_cpu(cpu)
+	{
+		per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
+		if (per_cpu(balloon_scratch_page, cpu) == NULL) {
+			pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
+			return -ENOMEM;
+		}
+	}
+	register_cpu_notifier(&balloon_cpu_notifier);
+
 	pr_info("Initialising balloon driver\n");
 
 	balloon_stats.current_pages = xen_pv_domain()
@@ -616,4 +673,15 @@ static int __init balloon_init(void)
 
 subsys_initcall(balloon_init);
 
+static int __init balloon_clear(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(balloon_scratch_page, cpu) = NULL;
+
+	return 0;
+}
+early_initcall(balloon_clear);
+
 MODULE_LICENSE("GPL");
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 5e8be462aed..4035e833ea2 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -56,6 +56,7 @@
 #include <xen/interface/hvm/params.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/sched.h>
+#include <xen/interface/vcpu.h>
 #include <asm/hw_irq.h>
 
 /*
@@ -1212,7 +1213,17 @@ EXPORT_SYMBOL_GPL(evtchn_put);
 
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 {
-	int irq = per_cpu(ipi_to_irq, cpu)[vector];
+	int irq;
+
+#ifdef CONFIG_X86
+	if (unlikely(vector == XEN_NMI_VECTOR)) {
+		int rc =  HYPERVISOR_vcpu_op(VCPUOP_send_nmi, cpu, NULL);
+		if (rc < 0)
+			printk(KERN_WARNING "Sending nmi to CPU%d failed (rc:%d)\n", cpu, rc);
+		return;
+	}
+#endif
+	irq = per_cpu(ipi_to_irq, cpu)[vector];
 	BUG_ON(irq < 0);
 	notify_remote_via_irq(irq);
 }
@@ -1379,14 +1390,21 @@ static void __xen_evtchn_do_upcall(void)
 
 			pending_bits = active_evtchns(cpu, s, word_idx);
 			bit_idx = 0; /* usually scan entire word from start */
+			/*
+			 * We scan the starting word in two parts.
+			 *
+			 * 1st time: start in the middle, scanning the
+			 * upper bits.
+			 *
+			 * 2nd time: scan the whole word (not just the
+			 * parts skipped in the first pass) -- if an
+			 * event in the previously scanned bits is
+			 * pending again it would just be scanned on
+			 * the next loop anyway.
+			 */
 			if (word_idx == start_word_idx) {
-				/* We scan the starting word in two parts */
 				if (i == 0)
-					/* 1st time: start in the middle */
 					bit_idx = start_bit_idx;
-				else
-					/* 2nd time: mask bits done already */
-					bit_idx &= (1UL << start_bit_idx) - 1;
 			}
 
 			do {
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index b6165e047f4..8b3a69a06c3 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -57,6 +57,7 @@
 
 struct per_user_data {
 	struct mutex bind_mutex; /* serialize bind/unbind operations */
+	struct rb_root evtchns;
 
 	/* Notification ring, accessed via /dev/xen/evtchn. */
 #define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
@@ -64,6 +65,7 @@ struct per_user_data {
 	evtchn_port_t *ring;
 	unsigned int ring_cons, ring_prod, ring_overflow;
 	struct mutex ring_cons_mutex; /* protect against concurrent readers */
+	spinlock_t ring_prod_lock; /* product against concurrent interrupts */
 
 	/* Processes wait on this queue when ring is empty. */
 	wait_queue_head_t evtchn_wait;
@@ -71,54 +73,79 @@ struct per_user_data {
 	const char *name;
 };
 
-/*
- * Who's bound to each port?  This is logically an array of struct
- * per_user_data *, but we encode the current enabled-state in bit 0.
- */
-static unsigned long *port_user;
-static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+struct user_evtchn {
+	struct rb_node node;
+	struct per_user_data *user;
+	unsigned port;
+	bool enabled;
+};
 
-static inline struct per_user_data *get_port_user(unsigned port)
+static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
-	return (struct per_user_data *)(port_user[port] & ~1);
-}
+	struct rb_node **new = &(u->evtchns.rb_node), *parent = NULL;
 
-static inline void set_port_user(unsigned port, struct per_user_data *u)
-{
-	port_user[port] = (unsigned long)u;
+	while (*new) {
+		struct user_evtchn *this;
+
+		this = container_of(*new, struct user_evtchn, node);
+
+		parent = *new;
+		if (this->port < evtchn->port)
+			new = &((*new)->rb_left);
+		else if (this->port > evtchn->port)
+			new = &((*new)->rb_right);
+		else
+			return -EEXIST;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&evtchn->node, parent, new);
+	rb_insert_color(&evtchn->node, &u->evtchns);
+
+	return 0;
 }
 
-static inline bool get_port_enabled(unsigned port)
+static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
-	return port_user[port] & 1;
+	rb_erase(&evtchn->node, &u->evtchns);
+	kfree(evtchn);
 }
 
-static inline void set_port_enabled(unsigned port, bool enabled)
+static struct user_evtchn *find_evtchn(struct per_user_data *u, unsigned port)
 {
-	if (enabled)
-		port_user[port] |= 1;
-	else
-		port_user[port] &= ~1;
+	struct rb_node *node = u->evtchns.rb_node;
+
+	while (node) {
+		struct user_evtchn *evtchn;
+
+		evtchn = container_of(node, struct user_evtchn, node);
+
+		if (evtchn->port < port)
+			node = node->rb_left;
+		else if (evtchn->port > port)
+			node = node->rb_right;
+		else
+			return evtchn;
+	}
+	return NULL;
 }
 
 static irqreturn_t evtchn_interrupt(int irq, void *data)
 {
-	unsigned int port = (unsigned long)data;
-	struct per_user_data *u;
-
-	spin_lock(&port_user_lock);
-
-	u = get_port_user(port);
+	struct user_evtchn *evtchn = data;
+	struct per_user_data *u = evtchn->user;
 
-	WARN(!get_port_enabled(port),
+	WARN(!evtchn->enabled,
 	     "Interrupt for port %d, but apparently not enabled; per-user %p\n",
-	     port, u);
+	     evtchn->port, u);
 
 	disable_irq_nosync(irq);
-	set_port_enabled(port, false);
+	evtchn->enabled = false;
+
+	spin_lock(&u->ring_prod_lock);
 
 	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
-		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = evtchn->port;
 		wmb(); /* Ensure ring contents visible */
 		if (u->ring_cons == u->ring_prod++) {
 			wake_up_interruptible(&u->evtchn_wait);
@@ -128,7 +155,7 @@ static irqreturn_t evtchn_interrupt(int irq, void *data)
 	} else
 		u->ring_overflow = 1;
 
-	spin_unlock(&port_user_lock);
+	spin_unlock(&u->ring_prod_lock);
 
 	return IRQ_HANDLED;
 }
@@ -229,20 +256,20 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf,
 	if (copy_from_user(kbuf, buf, count) != 0)
 		goto out;
 
-	spin_lock_irq(&port_user_lock);
+	mutex_lock(&u->bind_mutex);
 
 	for (i = 0; i < (count/sizeof(evtchn_port_t)); i++) {
 		unsigned port = kbuf[i];
+		struct user_evtchn *evtchn;
 
-		if (port < NR_EVENT_CHANNELS &&
-		    get_port_user(port) == u &&
-		    !get_port_enabled(port)) {
-			set_port_enabled(port, true);
+		evtchn = find_evtchn(u, port);
+		if (evtchn && !evtchn->enabled) {
+			evtchn->enabled = true;
 			enable_irq(irq_from_evtchn(port));
 		}
 	}
 
-	spin_unlock_irq(&port_user_lock);
+	mutex_unlock(&u->bind_mutex);
 
 	rc = count;
 
@@ -253,6 +280,8 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf,
 
 static int evtchn_bind_to_user(struct per_user_data *u, int port)
 {
+	struct user_evtchn *evtchn;
+	struct evtchn_close close;
 	int rc = 0;
 
 	/*
@@ -263,35 +292,46 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
 	 * interrupt handler yet, and our caller has already
 	 * serialized bind operations.)
 	 */
-	BUG_ON(get_port_user(port) != NULL);
-	set_port_user(port, u);
-	set_port_enabled(port, true); /* start enabled */
+
+	evtchn = kzalloc(sizeof(*evtchn), GFP_KERNEL);
+	if (!evtchn)
+		return -ENOMEM;
+
+	evtchn->user = u;
+	evtchn->port = port;
+	evtchn->enabled = true; /* start enabled */
+
+	rc = add_evtchn(u, evtchn);
+	if (rc < 0)
+		goto err;
 
 	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
-				       u->name, (void *)(unsigned long)port);
-	if (rc >= 0)
-		rc = evtchn_make_refcounted(port);
-	else {
-		/* bind failed, should close the port now */
-		struct evtchn_close close;
-		close.port = port;
-		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-			BUG();
-		set_port_user(port, NULL);
-	}
+				       u->name, evtchn);
+	if (rc < 0)
+		goto err;
 
+	rc = evtchn_make_refcounted(port);
+	return rc;
+
+err:
+	/* bind failed, should close the port now */
+	close.port = port;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+	del_evtchn(u, evtchn);
 	return rc;
 }
 
-static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+static void evtchn_unbind_from_user(struct per_user_data *u,
+				    struct user_evtchn *evtchn)
 {
-	int irq = irq_from_evtchn(port);
+	int irq = irq_from_evtchn(evtchn->port);
 
 	BUG_ON(irq < 0);
 
-	unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+	unbind_from_irqhandler(irq, evtchn);
 
-	set_port_user(port, NULL);
+	del_evtchn(u, evtchn);
 }
 
 static long evtchn_ioctl(struct file *file,
@@ -370,6 +410,7 @@ static long evtchn_ioctl(struct file *file,
 
 	case IOCTL_EVTCHN_UNBIND: {
 		struct ioctl_evtchn_unbind unbind;
+		struct user_evtchn *evtchn;
 
 		rc = -EFAULT;
 		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
@@ -380,29 +421,27 @@ static long evtchn_ioctl(struct file *file,
 			break;
 
 		rc = -ENOTCONN;
-		if (get_port_user(unbind.port) != u)
+		evtchn = find_evtchn(u, unbind.port);
+		if (!evtchn)
 			break;
 
 		disable_irq(irq_from_evtchn(unbind.port));
-
-		evtchn_unbind_from_user(u, unbind.port);
-
+		evtchn_unbind_from_user(u, evtchn);
 		rc = 0;
 		break;
 	}
 
 	case IOCTL_EVTCHN_NOTIFY: {
 		struct ioctl_evtchn_notify notify;
+		struct user_evtchn *evtchn;
 
 		rc = -EFAULT;
 		if (copy_from_user(&notify, uarg, sizeof(notify)))
 			break;
 
-		if (notify.port >= NR_EVENT_CHANNELS) {
-			rc = -EINVAL;
-		} else if (get_port_user(notify.port) != u) {
-			rc = -ENOTCONN;
-		} else {
+		rc = -ENOTCONN;
+		evtchn = find_evtchn(u, notify.port);
+		if (evtchn) {
 			notify_remote_via_evtchn(notify.port);
 			rc = 0;
 		}
@@ -412,9 +451,9 @@ static long evtchn_ioctl(struct file *file,
 	case IOCTL_EVTCHN_RESET: {
 		/* Initialise the ring to empty. Clear errors. */
 		mutex_lock(&u->ring_cons_mutex);
-		spin_lock_irq(&port_user_lock);
+		spin_lock_irq(&u->ring_prod_lock);
 		u->ring_cons = u->ring_prod = u->ring_overflow = 0;
-		spin_unlock_irq(&port_user_lock);
+		spin_unlock_irq(&u->ring_prod_lock);
 		mutex_unlock(&u->ring_cons_mutex);
 		rc = 0;
 		break;
@@ -473,6 +512,7 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 
 	mutex_init(&u->bind_mutex);
 	mutex_init(&u->ring_cons_mutex);
+	spin_lock_init(&u->ring_prod_lock);
 
 	filp->private_data = u;
 
@@ -481,15 +521,15 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 
 static int evtchn_release(struct inode *inode, struct file *filp)
 {
-	int i;
 	struct per_user_data *u = filp->private_data;
+	struct rb_node *node;
 
-	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
-		if (get_port_user(i) != u)
-			continue;
+	while ((node = u->evtchns.rb_node)) {
+		struct user_evtchn *evtchn;
 
-		disable_irq(irq_from_evtchn(i));
-		evtchn_unbind_from_user(get_port_user(i), i);
+		evtchn = rb_entry(node, struct user_evtchn, node);
+		disable_irq(irq_from_evtchn(evtchn->port));
+		evtchn_unbind_from_user(u, evtchn);
 	}
 
 	free_page((unsigned long)u->ring);
@@ -523,12 +563,6 @@ static int __init evtchn_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	port_user = kcalloc(NR_EVENT_CHANNELS, sizeof(*port_user), GFP_KERNEL);
-	if (port_user == NULL)
-		return -ENOMEM;
-
-	spin_lock_init(&port_user_lock);
-
 	/* Create '/dev/xen/evtchn'. */
 	err = misc_register(&evtchn_miscdev);
 	if (err != 0) {
@@ -543,9 +577,6 @@ static int __init evtchn_init(void)
 
 static void __exit evtchn_cleanup(void)
 {
-	kfree(port_user);
-	port_user = NULL;
-
 	misc_deregister(&evtchn_miscdev);
 }
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index eab5427c75f..e41c79c986e 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -272,19 +272,12 @@ static int map_grant_pages(struct grant_map *map)
 		 * with find_grant_ptes.
 		 */
 		for (i = 0; i < map->count; i++) {
-			unsigned level;
 			unsigned long address = (unsigned long)
 				pfn_to_kaddr(page_to_pfn(map->pages[i]));
-			pte_t *ptep;
-			u64 pte_maddr = 0;
 			BUG_ON(PageHighMem(map->pages[i]));
 
-			ptep = lookup_address(address, &level);
-			pte_maddr = arbitrary_virt_to_machine(ptep).maddr;
-			gnttab_set_map_op(&map->kmap_ops[i], pte_maddr,
-				map->flags |
-				GNTMAP_host_map |
-				GNTMAP_contains_pte,
+			gnttab_set_map_op(&map->kmap_ops[i], address,
+				map->flags | GNTMAP_host_map,
 				map->grants[i].ref,
 				map->grants[i].domid);
 		}
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 04cdeb8e371..c4d2298893b 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -730,9 +730,18 @@ void gnttab_request_free_callback(struct gnttab_free_callback *callback,
 				  void (*fn)(void *), void *arg, u16 count)
 {
 	unsigned long flags;
+	struct gnttab_free_callback *cb;
+
 	spin_lock_irqsave(&gnttab_list_lock, flags);
-	if (callback->next)
-		goto out;
+
+	/* Check if the callback is already on the list */
+	cb = gnttab_free_callback_list;
+	while (cb) {
+		if (cb == callback)
+			goto out;
+		cb = cb->next;
+	}
+
 	callback->fn = fn;
 	callback->arg = arg;
 	callback->count = count;
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index f8e5dd701ec..8e74590fa1b 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -43,9 +43,10 @@ MODULE_LICENSE("GPL");
 
 #define PRIV_VMA_LOCKED ((void *)1)
 
-#ifndef HAVE_ARCH_PRIVCMD_MMAP
-static int privcmd_enforce_singleshot_mapping(st