Merge tag 'stable/for-linus-3.5-rc0-tag' of...

Merge tag 'stable/for-linus-3.5-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull Xen updates from Konrad Rzeszutek Wilk:
 "Features:
   * Extend the APIC ops implementation and add IRQ_WORKER vector
     support so that 'perf' can work properly.
   * Fix self-ballooning code, and balloon logic when booting as initial
     domain.
   * Move array printing code to generic debugfs
   * Support XenBus domains.
   * Lazily free grants when a domain is dead/non-existent.
   * In M2P code use batching calls
  Bug-fixes:
   * Fix NULL dereference in allocation failure path (hvc_xen)
   * Fix unbinding of IRQ_WORKER vector during vCPU hot-unplug
   * Fix HVM guest resume - we would leak an PIRQ value instead of
     reusing the existing one."

Fix up add-add onflicts in arch/x86/xen/enlighten.c due to addition of
apic ipi interface next to the new apic_id functions.

* tag 'stable/for-linus-3.5-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen: do not map the same GSI twice in PVHVM guests.
  hvc_xen: NULL dereference on allocation failure
  xen: Add selfballoning memory reservation tunable.
  xenbus: Add support for xenbus backend in stub domain
  xen/smp: unbind irqworkX when unplugging vCPUs.
  xen: enter/exit lazy_mmu_mode around m2p_override calls
  xen/acpi/sleep: Enable ACPI sleep via the __acpi_os_prepare_sleep
  xen: implement IRQ_WORK_VECTOR handler
  xen: implement apic ipi interface
  xen/setup: update VA mapping when releasing memory during setup
  xen/setup: Combine the two hypercall functions - since they are quite similar.
  xen/setup: Populate freed MFNs from non-RAM E820 entries and gaps to E820 RAM
  xen/setup: Only print "Freeing XXX-YYY pfn range: Z pages freed" if Z > 0
  xen/gnttab: add deferred freeing logic
  debugfs: Add support to print u32 array in debugfs
  xen/p2m: An early bootup variant of set_phys_to_machine
  xen/p2m: Collapse early_alloc_p2m_middle redundant checks.
  xen/p2m: Allow alloc_p2m_middle to call reserve_brk depending on argument
  xen/p2m: Move code around to allow for better re-usage.

arch/x86/include/asm/xen/events.h

@@ -6,6 +6,7 @@ enum ipi_vector {
 	XEN_CALL_FUNCTION_VECTOR,
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 	XEN_SPIN_UNLOCK_VECTOR,
+	XEN_IRQ_WORK_VECTOR,
 
 	XEN_NR_IPIS,
 };

arch/x86/include/asm/xen/page.h

@@ -44,6 +44,7 @@ extern unsigned long  machine_to_phys_nr;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 					     unsigned long pfn_e);

arch/x86/pci/xen.c

@@ -64,6 +64,10 @@ static int xen_register_pirq(u32 gsi, int gsi_override, int triggering,
 	int shareable = 0;
 	char *name;
 
+	irq = xen_irq_from_gsi(gsi);
+	if (irq > 0)
+		return irq;
+
 	if (set_pirq)
 		pirq = gsi;
 

arch/x86/xen/debugfs.c

@@ -19,107 +19,3 @@ struct dentry * __init xen_init_debugfs(void)
 	return d_xen_debug;
 }
 
-struct array_data
-{
-	void *array;
-	unsigned elements;
-};
-
-static int u32_array_open(struct inode *inode, struct file *file)
-{
-	file->private_data = NULL;
-	return nonseekable_open(inode, file);
-}
-
-static size_t format_array(char *buf, size_t bufsize, const char *fmt,
-			   u32 *array, unsigned array_size)
-{
-	size_t ret = 0;
-	unsigned i;
-
-	for(i = 0; i < array_size; i++) {
-		size_t len;
-
-		len = snprintf(buf, bufsize, fmt, array[i]);
-		len++;	/* ' ' or '\n' */
-		ret += len;
-
-		if (buf) {
-			buf += len;
-			bufsize -= len;
-			buf[-1] = (i == array_size-1) ? '\n' : ' ';
-		}
-	}
-
-	ret++;		/* \0 */
-	if (buf)
-		*buf = '\0';
-
-	return ret;
-}
-
-static char *format_array_alloc(const char *fmt, u32 *array, unsigned array_size)
-{
-	size_t len = format_array(NULL, 0, fmt, array, array_size);
-	char *ret;
-
-	ret = kmalloc(len, GFP_KERNEL);
-	if (ret == NULL)
-		return NULL;
-
-	format_array(ret, len, fmt, array, array_size);
-	return ret;
-}
-
-static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
-			      loff_t *ppos)
-{
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct array_data *data = inode->i_private;
-	size_t size;
-
-	if (*ppos == 0) {
-		if (file->private_data) {
-			kfree(file->private_data);
-			file->private_data = NULL;
-		}
-
-		file->private_data = format_array_alloc("%u", data->array, data->elements);
-	}
-
-	size = 0;
-	if (file->private_data)
-		size = strlen(file->private_data);
-
-	return simple_read_from_buffer(buf, len, ppos, file->private_data, size);
-}
-
-static int xen_array_release(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
-
-	return 0;
-}
-
-static const struct file_operations u32_array_fops = {
-	.owner	= THIS_MODULE,
-	.open	= u32_array_open,
-	.release= xen_array_release,
-	.read	= u32_array_read,
-	.llseek = no_llseek,
-};
-
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements)
-{
-	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
-
-	if (data == NULL)
-		return NULL;
-
-	data->array = array;
-	data->elements = elements;
-
-	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
-}

arch/x86/xen/debugfs.h

@@ -3,8 +3,4 @@
 
 struct dentry * __init xen_init_debugfs(void);
 
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements);
-
 #endif /* _XEN_DEBUGFS_H */

arch/x86/xen/enlighten.c

@@ -42,6 +42,7 @@
 #include <xen/page.h>
 #include <xen/hvm.h>
 #include <xen/hvc-console.h>
+#include <xen/acpi.h>
 
 #include <asm/paravirt.h>
 #include <asm/apic.h>
@@ -75,6 +76,7 @@
 
 #include "xen-ops.h"
 #include "mmu.h"
+#include "smp.h"
 #include "multicalls.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
@@ -883,6 +885,14 @@ static void set_xen_basic_apic_ops(void)
 	apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
 	apic->set_apic_id = xen_set_apic_id;
 	apic->get_apic_id = xen_get_apic_id;
+
+#ifdef CONFIG_SMP
+	apic->send_IPI_allbutself = xen_send_IPI_allbutself;
+	apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself;
+	apic->send_IPI_mask = xen_send_IPI_mask;
+	apic->send_IPI_all = xen_send_IPI_all;
+	apic->send_IPI_self = xen_send_IPI_self;
+#endif
 }
 
 #endif
@@ -1340,7 +1350,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
-	xen_ident_map_ISA();
 
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
@@ -1400,6 +1409,8 @@ asmlinkage void __init xen_start_kernel(void)
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
+
+		xen_acpi_sleep_register();
 	}
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */

arch/x86/xen/mmu.c

@@ -1933,29 +1933,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
-void __init xen_ident_map_ISA(void)
-{
-	unsigned long pa;
-
-	/*
-	 * If we're dom0, then linear map the ISA machine addresses into
-	 * the kernel's address space.
-	 */
-	if (!xen_initial_domain())
-		return;
-
-	xen_raw_printk("Xen: setup ISA identity maps\n");
-
-	for (pa = ISA_START_ADDRESS; pa < ISA_END_ADDRESS; pa += PAGE_SIZE) {
-		pte_t pte = mfn_pte(PFN_DOWN(pa), PAGE_KERNEL_IO);
-
-		if (HYPERVISOR_update_va_mapping(PAGE_OFFSET + pa, pte, 0))
-			BUG();
-	}
-
-	xen_flush_tlb();
-}
-
 static void __init xen_post_allocator_init(void)
 {
 	pv_mmu_ops.set_pte = xen_set_pte;

arch/x86/xen/p2m.c

@@ -499,16 +499,18 @@ static bool alloc_p2m(unsigned long pfn)
 	return true;
 }
 
-static bool __init __early_alloc_p2m(unsigned long pfn)
+static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary)
 {
 	unsigned topidx, mididx, idx;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
 
 	topidx = p2m_top_index(pfn);
 	mididx = p2m_mid_index(pfn);
 	idx = p2m_index(pfn);
 
 	/* Pfff.. No boundary cross-over, lets get out. */
-	if (!idx)
+	if (!idx && check_boundary)
 		return false;
 
 	WARN(p2m_top[topidx][mididx] == p2m_identity,
@@ -522,9 +524,7 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
 		return false;
 
 	/* Boundary cross-over for the edges: */
-	if (idx) {
-		unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		unsigned long *mid_mfn_p;
+	p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
 	p2m_init(p2m);
 
@@ -538,27 +538,11 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
 		topidx, mididx);
 	mid_mfn_p[mididx] = virt_to_mfn(p2m);
 
-	}
-	return idx != 0;
+	return true;
 }
-unsigned long __init set_phys_range_identity(unsigned long pfn_s,
-				      unsigned long pfn_e)
-{
-	unsigned long pfn;
-
-	if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
-		return 0;
-
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
-		return pfn_e - pfn_s;
-
-	if (pfn_s > pfn_e)
-		return 0;
 
-	for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
-		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
-		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
-	{
+static bool __init early_alloc_p2m(unsigned long pfn)
+{
 	unsigned topidx = p2m_top_index(pfn);
 	unsigned long *mid_mfn_p;
 	unsigned long **mid;
@@ -582,12 +566,48 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 		p2m_top_mfn_p[topidx] = mid_mfn_p;
 		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
 		/* Note: we don't set mid_mfn_p[midix] here,
-		 	 * look in __early_alloc_p2m */
+		 * look in early_alloc_p2m_middle */
 	}
+	return true;
+}
+bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
+		if (!early_alloc_p2m(pfn))
+			return false;
+
+		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
+			return false;
+
+		if (!__set_phys_to_machine(pfn, mfn))
+			return false;
+	}
+
+	return true;
+}
+unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+				      unsigned long pfn_e)
+{
+	unsigned long pfn;
+
+	if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+		return 0;
+
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
+		return pfn_e - pfn_s;
+
+	if (pfn_s > pfn_e)
+		return 0;
+
+	for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
+		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
+		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
+	{
+		WARN_ON(!early_alloc_p2m(pfn));
 	}
 
-	__early_alloc_p2m(pfn_s);
-	__early_alloc_p2m(pfn_e);
+	early_alloc_p2m_middle(pfn_s, true);
+	early_alloc_p2m_middle(pfn_e, true);
 
 	for (pfn = pfn_s; pfn < pfn_e; pfn++)
 		if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))

arch/x86/xen/setup.c

@@ -26,7 +26,6 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
-
 #include "xen-ops.h"
 #include "vdso.h"
 
@@ -84,8 +83,8 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 }
 
-static unsigned long __init xen_release_chunk(unsigned long start,
-					      unsigned long end)
+static unsigned long __init xen_do_chunk(unsigned long start,
+					 unsigned long end, bool release)
 {
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
@@ -96,30 +95,138 @@ static unsigned long __init xen_release_chunk(unsigned long start,
 	unsigned long pfn;
 	int ret;
 
-	for(pfn = start; pfn < end; pfn++) {
+	for (pfn = start; pfn < end; pfn++) {
+		unsigned long frame;
 		unsigned long mfn = pfn_to_mfn(pfn);
 
+		if (release) {
 			/* Make sure pfn exists to start with */
 			if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
 				continue;
-
-		set_xen_guest_handle(reservation.extent_start, &mfn);
+			frame = mfn;
+		} else {
+			if (mfn != INVALID_P2M_ENTRY)
+				continue;
+			frame = pfn;
+		}
+		set_xen_guest_handle(reservation.extent_start, &frame);
 		reservation.nr_extents = 1;
 
-		ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+		ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
 					   &reservation);
-		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
+		WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
+		     release ? "release" : "populate", pfn, ret);
+
 		if (ret == 1) {
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-			len++;
+			if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
+				if (release)
+					break;
+				set_xen_guest_handle(reservation.extent_start, &frame);
+				reservation.nr_extents = 1;
+				ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+							   &reservation);
+				break;
 			}
+			len++;
+		} else
+			break;
 	}
-	printk(KERN_INFO "Freeing  %lx-%lx pfn range: %lu pages freed\n",
-	       start, end, len);
+	if (len)
+		printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
+		       release ? "Freeing" : "Populating",
+		       start, end, len,
+		       release ? "freed" : "added");
 
 	return len;
 }
 
+static unsigned long __init xen_release_chunk(unsigned long start,
+					      unsigned long end)
+{
+	return xen_do_chunk(start, end, true);
+}
+
+static unsigned long __init xen_populate_chunk(
+	const struct e820entry *list, size_t map_size,
+	unsigned long max_pfn, unsigned long *last_pfn,
+	unsigned long credits_left)
+{
+	const struct e820entry *entry;
+	unsigned int i;
+	unsigned long done = 0;
+	unsigned long dest_pfn;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		unsigned long credits = credits_left;
+		unsigned long s_pfn;
+		unsigned long e_pfn;
+		unsigned long pfns;
+		long capacity;
+
+		if (credits <= 0)
+			break;
+
+		if (entry->type != E820_RAM)
+			continue;
+
+		e_pfn = PFN_UP(entry->addr + entry->size);
+
+		/* We only care about E820 after the xen_start_info->nr_pages */
+		if (e_pfn <= max_pfn)
+			continue;
+
+		s_pfn = PFN_DOWN(entry->addr);
+		/* If the E820 falls within the nr_pages, we want to start
+		 * at the nr_pages PFN.
+		 * If that would mean going past the E820 entry, skip it
+		 */
+		if (s_pfn <= max_pfn) {
+			capacity = e_pfn - max_pfn;
+			dest_pfn = max_pfn;
+		} else {
+			/* last_pfn MUST be within E820_RAM regions */
+			if (*last_pfn && e_pfn >= *last_pfn)
+				s_pfn = *last_pfn;
+			capacity = e_pfn - s_pfn;
+			dest_pfn = s_pfn;
+		}
+		/* If we had filled this E820_RAM entry, go to the next one. */
+		if (capacity <= 0)
+			continue;
+
+		if (credits > capacity)
+			credits = capacity;
+
+		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+		done += pfns;
+		credits_left -= pfns;
+		*last_pfn = (dest_pfn + pfns);
+	}
+	return done;
+}
+
+static void __init xen_set_identity_and_release_chunk(
+	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+	unsigned long *released, unsigned long *identity)
+{
+	unsigned long pfn;
+
+	/*
+	 * If the PFNs are currently mapped, the VA mapping also needs
+	 * to be updated to be 1:1.
+	 */
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+		(void)HYPERVISOR_update_va_mapping(
+			(unsigned long)__va(pfn << PAGE_SHIFT),
+			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+
+	if (start_pfn < nr_pages)
+		*released += xen_release_chunk(
+			start_pfn, min(end_pfn, nr_pages));
+
+	*identity += set_phys_range_identity(start_pfn, end_pfn);
+}
+
 static unsigned long __init xen_set_identity_and_release(
 	const struct e820entry *list, size_t map_size, unsigned long nr_pages)
 {
@@ -142,7 +249,6 @@ static unsigned long __init xen_set_identity_and_release(
 	 */
 	for (i = 0, entry = list; i < map_size; i++, entry++) {
 		phys_addr_t end = entry->addr + entry->size;
-
 		if (entry->type == E820_RAM || i == map_size - 1) {
 			unsigned long start_pfn = PFN_DOWN(start);
 			unsigned long end_pfn = PFN_UP(end);
@@ -150,19 +256,18 @@ static unsigned long __init xen_set_identity_and_release(
 			if (entry->type == E820_RAM)
 				end_pfn = PFN_UP(entry->addr);
 
-			if (start_pfn < end_pfn) {
-				if (start_pfn < nr_pages)
-					released += xen_release_chunk(
-						start_pfn, min(end_pfn, nr_pages));
+			if (start_pfn < end_pfn)
+				xen_set_identity_and_release_chunk(
+					start_pfn, end_pfn, nr_pages,
+					&released, &identity);
 
-				identity += set_phys_range_identity(
-					start_pfn, end_pfn);
-			}
 			start = end;
 		}
 	}
 
+	if (released)
 		printk(KERN_INFO "Released %lu pages of unused memory\n", released);
+	if (identity)
 		printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
 
 	return released;
@@ -217,7 +322,9 @@ char * __init xen_memory_setup(void)
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
+	unsigned long last_pfn = 0;
 	unsigned long extra_pages = 0;
+	unsigned long populated;
 	int i;
 	int op;
 
@@ -257,8 +364,19 @@ char * __init xen_memory_setup(void)
 	 */
 	xen_released_pages = xen_set_identity_and_release(
 		map, memmap.nr_entries, max_pfn);
-	extra_pages += xen_released_pages;
 
+	/*
+	 * Populate back the non-RAM pages and E820 gaps that had been
+	 * released. */
+	populated = xen_populate_chunk(map, memmap.nr_entries,
+			max_pfn, &last_pfn, xen_released_pages);
+
+	extra_pages += (xen_released_pages - populated);
+
+	if (last_pfn > max_pfn) {
+		max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
+		mem_end = PFN_PHYS(max_pfn);
+	}
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
 	 * factor the base size.  On non-highmem systems, the base
@@ -272,7 +390,6 @@ char * __init xen_memory_setup(void)
 	 */
 	extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
 			  extra_pages);
-
 	i = 0;
 	while (i < memmap.nr_entries) {
 		u64 addr = map[i].addr;

arch/x86/xen/smp.c

@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
+#include <linux/irq_work.h>
 
 #include <asm/paravirt.h>
 #include <asm/desc.h>
@@ -41,10 +42,12 @@ cpumask_var_t xen_cpu_initialized_map;
 static DEFINE_PER_CPU(int, xen_resched_irq);
 static DEFINE_PER_CPU(int, xen_callfunc_irq);
 static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
+static DEFINE_PER_CPU(int, xen_irq_work);
 static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
 
 /*
  * Reschedule call back.
@@ -143,6 +146,17 @@ static int xen_smp_intr_init(unsigned int cpu)
 		goto fail;
 	per_cpu(xen_callfuncsingle_irq, cpu) = rc;
 
+	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
+				    cpu,
+				    xen_irq_work_interrupt,
+				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    callfunc_name,
+				    NULL);
+	if (rc < 0)
+		goto fail;
+	per_cpu(xen_irq_work, cpu) = rc;
+
 	return 0;
 
  fail:
@@ -155,6 +169,8 @@ static int xen_smp_intr_init(unsigned int cpu)
 	if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
 		unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
 				       NULL);
+	if (per_cpu(xen_irq_work, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
 
 	return rc;
 }
@@ -407,6 +423,7 @@ static void xen_cpu_die(unsigned int cpu)
 	unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
 	xen_uninit_lock_cpu(cpu);
 	xen_teardown_timer(cpu);
 
@@ -469,8 +486,8 @@ static void xen_smp_send_reschedule(int cpu)
 	xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
 }
 
-static void xen_send_IPI_mask(const struct cpumask *mask,
-			      enum ipi_vector vector)
+static void __xen_send_IPI_mask(const struct cpumask *mask,
+			      int vector)
 {
 	unsigned cpu;
 
@@ -482,7 +499,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
 {
 	int cpu;
 
-	xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
+	__xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
 
 	/* Make sure other vcpus get a chance to run if they need to. */
 	for_each_cpu(cpu, mask) {
@@ -495,10 +512,86 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
 
 static void xen_smp_send_call_function_single_ipi(int cpu)
 {
-	xen_send_IPI_mask(cpumask_of(cpu),
+	__xen_send_IPI_mask(cpumask_of(cpu),
 			  XEN_CALL_FUNCTION_SINGLE_VECTOR);
 }
 
+static inline int xen_map_vector(int vector)
+{
+	int xen_vector;
+
+	switch (vector) {
+	case RESCHEDULE_VECTOR:
+		xen_vector = XEN_RESCHEDULE_VECTOR;
+		break;
+	case CALL_FUNCTION_VECTOR:
+		xen_vector = XEN_CALL_FUNCTION_VECTOR;
+		break;
+	case CALL_FUNCTION_SINGLE_VECTOR:
+		xen_vector = XEN_CALL_FUNCTION_SINGLE_VECTOR;
+		break;
+	case IRQ_WORK_VECTOR:
+		xen_vector = XEN_IRQ_WORK_VECTOR;
+		break;
+	default:
+		xen_vector = -1;
+		printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
+			vector);
+	}
+
+	return xen_vector;
+}
+
+void xen_send_IPI_mask(const struct cpumask *mask,
+			      int vector)
+{
+	int xen_vector = xen_map_vector(vector);
+
+	if (xen_vector >= 0)
+		__xen_send_IPI_mask(mask, xen_vector);
+}
+
+void xen_send_IPI_all(int vector)
+{
+	int xen_vector = xen_map_vector(vector);
+
+	if (xen_vector >= 0)
+		__xen_send_IPI_mask(cpu_online_mask, xen_vector);
+}
+
+void xen_send_IPI_self(int vector)
+{
+	int xen_vector = xen_map_vector(vector);
+
+	if (xen_vector >= 0)
+		xen_send_IPI_one(smp_processor_id(), xen_vector);
+}
+
+void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
+				int vector)
+{
+	unsigned cpu;
+	unsigned int this_cpu = smp_processor_id();
+
+	if (!(num_online_cpus() > 1))
+		return;
+
+	for_each_cpu_and(cpu, mask, cpu_online_mask) {
+		if (this_cpu == cpu)
+			continue;
+
+		xen_smp_send_call_function_single_ipi(cpu);
+	}
+}
+
+void xen_send_IPI_allbutself(int vector)
+{
+	int xen_vector = xen_map_vector(vector);
+
+	if (xen_vector >= 0)
+		xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+}
+
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 {
 	irq_enter();
@@ -519,6 +612,16 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
+{
+	irq_enter();
+	irq_work_run();
+	inc_irq_stat(apic_irq_work_irqs);
+	irq_exit();
+
+	return IRQ_HANDLED;
+}
+
 static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_smp_prepare_cpus,
@@ -565,6 +668,7 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 	unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
 	native_cpu_die(cpu);
 }
 

arch/x86/xen/smp.h

+#ifndef _XEN_SMP_H
+
+extern void xen_send_IPI_mask(const struct cpumask *mask,
+			      int vector);
+extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
+				int vector);
+extern void xen_send_IPI_allbutself(int vector);
+extern void physflat_send_IPI_allbutself(int vector);
+extern void xen_send_IPI_all(int vector);
+extern void xen_send_IPI_self(int vector);
+
+#endif

arch/x86/xen/spinlock.c

@@ -440,11 +440,11 @@ static int __init xen_spinlock_debugfs(void)
 	debugfs_create_u64("time_total", 0444, d_spin_debug,
 			   &spinlock_stats.time_total);
 
-	xen_debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
+	debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
 				spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
-	xen_debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
+	debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
 				spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
-	xen_debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
 				spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
 
 	return 0;

arch/x86/xen/xen-ops.h

@@ -28,7 +28,6 @@ void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
-void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 extern unsigned long xen_max_p2m_pfn;
 

drivers/xen/Makefile

@@ -17,7 +17,7 @@ obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 obj-$(CONFIG_XEN_PVHVM)			+= 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_DOM0)			+= pci.o acpi.o
 obj-$(CONFIG_XEN_PCIDEV_BACKEND)	+= xen-pciback/
 obj-$(CONFIG_XEN_PRIVCMD)		+= xen-privcmd.o
 obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o

drivers/xen/acpi.c

+/******************************************************************************
+ * acpi.c
+ * acpi file for domain 0 kernel
+ *
+ * Copyright (c) 2011 Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ * Copyright (c) 2011 Yu Ke ke.yu@intel.com
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <xen/acpi.h>
+#include <xen/interface/platform.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+int xen_acpi_notify_hypervisor_state(u8 sleep_state,
+				     u32 pm1a_cnt, u32 pm1b_cnt)
+{
+	struct xen_platform_op op = {
+		.cmd = XENPF_enter_acpi_sleep,
+		.interface_version = XENPF_INTERFACE_VERSION,
+		.u = {
+			.enter_acpi_sleep = {
+				.pm1a_cnt_val = (u16)pm1a_cnt,
+				.pm1b_cnt_val = (u16)pm1b_cnt,
+				.sleep_state = sleep_state,
+			},
+		},
+	};
+
+	if ((pm1a_cnt & 0xffff0000) || (pm1b_cnt & 0xffff0000)) {
+		WARN(1, "Using more than 16bits of PM1A/B 0x%x/0x%x!"
+		     "Email xen-devel@lists.xensource.com  Thank you.\n", \
+		     pm1a_cnt, pm1b_cnt);
+		return -1;
+	}
+
+	HYPERVISOR_dom0_op(&op);
+	return 1;
+}

drivers/xen/events.c

@@ -611,7 +611,7 @@ static void disable_pirq(struct irq_data *data)
 	disable_dynirq(data);
 }
 
-static int find_irq_by_gsi(unsigned gsi)
+int xen_irq_from_gsi(unsigned gsi)
 {
 	struct irq_info *info;
 
@@ -625,6 +625,7 @@ static int find_irq_by_gsi(unsigned gsi)
 
 	return -1;
 }
+EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 
 /*
  * Do not make any assumptions regarding the relationship between the
@@ -644,7 +645,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = find_irq_by_gsi(gsi);
+	irq = xen_irq_from_gsi(gsi);
 	if (irq != -1) {
 		printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
 		       irq, gsi);

drivers/xen/grant-table.c

@@ -38,6 +38,7 @@
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/hardirq.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -426,10 +427,8 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
 	nflags = *pflags;
 	do {
 		flags = nflags;
-		if (flags & (GTF_reading|GTF_writing)) {
-			printk(KERN_ALERT "WARNING: g.e. still in use!\n");
+		if (flags & (GTF_reading|GTF_writing))
 			return 0;
-		}
 	} while ((nflags = sync_cmpxchg(pflags, flags, 0)) != flags);
 
 	return 1;
@@ -458,12 +457,103 @@ static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
 	return 1;
 }
 
-int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
 {
 	return gnttab_interface->end_foreign_access_ref(ref, readonly);
 }
+
+int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+{
+	if (_gnttab_end_foreign_access_ref(ref, readonly))
+		return 1;
+	pr_warn("WARNING: g.e. %#x still in use!\n", ref);
+	return 0;
+}
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
 
+struct deferred_entry {
+	struct list_head list;
+	grant_ref_t ref;
+	bool ro;
+	uint16_t warn_delay;
+	struct page *page;
+};
+static LIST_HEAD(deferred_list);
+static void gnttab_handle_deferred(unsigned long);
+static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred, 0, 0);
+
+static void gnttab_handle_deferred(unsigned long unused)
+{
+	unsigned int nr = 10;
+	struct deferred_entry *first = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gnttab_list_lock, flags);
+	while (nr--) {
+		struct deferred_entry *entry
+			= list_first_entry(&deferred_list,
+					   struct deferred_entry, list);
+
+		if (entry == first)
+			break;
+		list_del(&entry->list);
+		spin_unlock_irqrestore(&gnttab_list_lock, flags);
+		if (_gnttab_end_foreign_access_ref(entry->ref, entry->ro)) {
+			put_free_entry(entry->ref);
+			if (entry->page) {
+				pr_debug("freeing g.e. %#x (pfn %#lx)\n",
+					 entry->ref, page_to_pfn(entry->page));
+				__free_page(entry->page);
+			} else
+				pr_info("freeing g.e. %#x\n", entry->ref);
+			kfree(entry);
+			entry = NULL;
+		} else {
+			if (!--entry->warn_delay)
+				pr_info("g.e. %#x still pending\n",
+					entry->ref);
+			if (!first)
+				first = entry;
+		}
+		spin_lock_irqsave(&gnttab_list_lock, flags);
+		if (entry)
+			list_add_tail(&entry->list, &deferred_list);
+		else if (list_empty(&deferred_list))
+			break;
+	}
+	if (!list_empty(&deferred_list) && !timer_pending(&deferred_timer)) {
+		deferred_timer.expires = jiffies + HZ;
+		add_timer(&deferred_timer);
+	}
+	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+
+static void gnttab_add_deferred(grant_ref_t ref, bool readonly,
+				struct page *page)
+{
+	struct deferred_entry *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	const char *what = KERN_WARNING "leaking";
+
+	if (entry) {
+		unsigned long flags;
+
+		entry->ref = ref;
+		entry->ro = readonly;
+		entry->page = page;
+		entry->warn_delay = 60;
+		spin_lock_irqsave(&gnttab_list_lock, flags);
+		list_add_tail(&entry->list, &deferred_list);
+		if (!timer_pending(&deferred_timer)) {
+			deferred_timer.expires = jiffies + HZ;
+			add_timer(&deferred_timer);
+		}
+		spin_unlock_irqrestore(&gnttab_list_lock, flags);
+		what = KERN_DEBUG "deferring";
+	}
+	printk("%s g.e. %#x (pfn %#lx)\n",
+	       what, ref, page ? page_to_pfn(page) : -1);
+}
+
 void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
 			       unsigned long page)
 {
@@ -471,12 +561,9 @@ void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
 		put_free_entry(ref);
 		if (page != 0)
 			free_page(page);
-	} else {
-		/* XXX This needs to be fixed so that the ref and page are
-		   placed on a list to be freed up later. */
-		printk(KERN_WARNING
-		       "WARNING: leaking g.e. and page still in use!\n");
-	}
+	} else
+		gnttab_add_deferred(ref, readonly,
+				    page ? virt_to_page(page) : NULL);
 }
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_access);
 
@@ -741,6 +828,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct page **pages, unsigned int count)
 {
 	int i, ret;
+	bool lazy = false;
 	pte_t *pte;
 	unsigned long mfn;
 
@@ -751,6 +839,11 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return ret;
 
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+		arch_enter_lazy_mmu_mode();
+		lazy = true;
+	}
+
 	for (i = 0; i < count; i++) {
 		/* Do not add to override if the map failed. */
 		if (map_ops[i].status)
@@ -769,6 +862,9 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 			return ret;
 	}
 
+	if (lazy)
+		arch_leave_lazy_mmu_mode();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(gnttab_map_refs);
@@ -777,6 +873,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct page **pages, unsigned int count, bool clear_pte)
 {
 	int i, ret;
+	bool lazy = false;
 
 	ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
 	if (ret)
@@ -785,12 +882,20 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return ret;
 
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+		arch_enter_lazy_mmu_mode();
+		lazy = true;
+	}
+
 	for (i = 0; i < count; i++) {
 		ret = m2p_remove_override(pages[i], clear_pte);
 		if (ret)
 			return ret;
 	}
 
+	if (lazy)
+		arch_leave_lazy_mmu_mode();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);

drivers/xen/xen-selfballoon.c

@@ -105,6 +105,12 @@ static unsigned int selfballoon_interval __read_mostly = 5;
  */
 static unsigned int selfballoon_min_usable_mb;
 
+/*
+ * Amount of RAM in MB to add to the target number of pages.
+ * Can be used to reserve some more room for caches and the like.
+ */
+static unsigned int selfballoon_reserved_mb;
+
 static void selfballoon_process(struct work_struct *work);
 static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
 
@@ -217,7 +223,8 @@ static void selfballoon_process(struct work_struct *work)
 		cur_pages = totalram_pages;
 		tgt_pages = cur_pages; /* default is no change */
 		goal_pages = percpu_counter_read_positive(&vm_committed_as) +
-				totalreserve_pages;
+				totalreserve_pages +
+				MB2PAGES(selfballoon_reserved_mb);
 #ifdef CONFIG_FRONTSWAP
 		/* allow space for frontswap pages to be repatriated */
 		if (frontswap_selfshrinking && frontswap_enabled)
@@ -397,6 +404,30 @@ static DEVICE_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
 		   show_selfballoon_min_usable_mb,
 		   store_selfballoon_min_usable_mb);
 
+SELFBALLOON_SHOW(selfballoon_reserved_mb, "%d\n",
+				selfballoon_reserved_mb);
+
+static ssize_t store_selfballoon_reserved_mb(struct device *dev,
+					     struct device_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_reserved_mb = val;
+	return count;
+}
+
+static DEVICE_ATTR(selfballoon_reserved_mb, S_IRUGO | S_IWUSR,
+		   show_selfballoon_reserved_mb,
+		   store_selfballoon_reserved_mb);
+
 
 #ifdef CONFIG_FRONTSWAP
 SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
@@ -480,6 +511,7 @@ static struct attribute *selfballoon_attrs[] = {
 	&dev_attr_selfballoon_downhysteresis.attr,
 	&dev_attr_selfballoon_uphysteresis.attr,
 	&dev_attr_selfballoon_min_usable_mb.attr,
+	&dev_attr_selfballoon_reserved_mb.attr,
 #ifdef CONFIG_FRONTSWAP
 	&dev_attr_frontswap_selfshrinking.attr,
 	&dev_attr_frontswap_hysteresis.attr,

drivers/xen/xenbus/xenbus_comms.c

@@ -234,3 +234,9 @@ int xb_init_comms(void)
 
 	return 0;
 }
+
+void xb_deinit_comms(void)
+{
+	unbind_from_irqhandler(xenbus_irq, &xb_waitq);
+	xenbus_irq = 0;
+}

drivers/xen/xenbus/xenbus_comms.h

@@ -35,6 +35,7 @@
 
 int xs_init(void);
 int xb_init_comms(void);
+void xb_deinit_comms(void);
 
 /* Low level routines. */
 int xb_write(const void *data, unsigned len);

drivers/xen/xenbus/xenbus_dev_backend.c

@@ -8,7 +8,11 @@
 
 #include <xen/xen.h>
 #include <xen/page.h>
+#include <xen/xenbus.h>
 #include <xen/xenbus_dev.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+#include <asm/xen/hypervisor.h>
 
 #include "xenbus_comms.h"
 
@@ -22,6 +26,50 @@ static int xenbus_backend_open(struct inode *inode, struct file *filp)
 	return nonseekable_open(inode, filp);
 }
 
+static long xenbus_alloc(domid_t domid)
+{
+	struct evtchn_alloc_unbound arg;
+	int err = -EEXIST;
+
+	xs_suspend();
+
+	/* If xenstored_ready is nonzero, that means we have already talked to
+	 * xenstore and set up watches. These watches will be restored by
+	 * xs_resume, but that requires communication over the port established
+	 * below that is not visible to anyone until the ioctl returns.
+	 *
+	 * This can be resolved by splitting the ioctl into two parts
+	 * (postponing the resume until xenstored is active) but this is
+	 * unnecessarily complex for the intended use where xenstored is only
+	 * started once - so return -EEXIST if it's already running.
+	 */
+	if (xenstored_ready)
+		goto out_err;
+
+	gnttab_grant_foreign_access_ref(GNTTAB_RESERVED_XENSTORE, domid,
+			virt_to_mfn(xen_store_interface), 0 /* writable */);
+
+	arg.dom = DOMID_SELF;
+	arg.remote_dom = domid;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound, &arg);
+	if (err)
+		goto out_err;
+
+	if (xen_store_evtchn > 0)
+		xb_deinit_comms();
+
+	xen_store_evtchn = arg.port;
+
+	xs_resume();
+
+	return arg.port;
+
+ out_err:
+	xs_suspend_cancel();
+	return err;
+}
+
 static long xenbus_backend_ioctl(struct file *file, unsigned int cmd, unsigned long data)
 {
 	if (!capable(CAP_SYS_ADMIN))
@@ -33,6 +81,9 @@ static long xenbus_backend_ioctl(struct file *file, unsigned int cmd, unsigned l
 				return xen_store_evtchn;
 			return -ENODEV;
 
+		case IOCTL_XENBUS_BACKEND_SETUP:
+			return xenbus_alloc(data);
+
 		default:
 			return -ENOTTY;
 	}

fs/debugfs/file.c

@@ -20,6 +20,7 @@
 #include <linux/namei.h>
 #include <linux/debugfs.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
@@ -520,6 +521,133 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_blob);
 
+struct array_data {
+	void *array;
+	u32 elements;
+};
+
+static int u32_array_open(struct inode *inode, struct file *file)
+{
+	file->private_data = NULL;
+	return nonseekable_open(inode, file);
+}
+
+static size_t format_array(char *buf, size_t bufsize, const char *fmt,
+			   u32 *array, u32 array_size)
+{
+	size_t ret = 0;
+	u32 i;
+
+	for (i = 0; i < array_size; i++) {
+		size_t len;
+
+		len = snprintf(buf, bufsize, fmt, array[i]);
+		len++;	/* ' ' or '\n' */
+		ret += len;
+
+		if (buf) {
+			buf += len;
+			bufsize -= len;
+			buf[-1] = (i == array_size-1) ? '\n' : ' ';
+		}
+	}
+
+	ret++;		/* \0 */
+	if (buf)
+		*buf = '\0';
+
+	return ret;
+}
+
+static char *format_array_alloc(const char *fmt, u32 *array,
+						u32 array_size)
+{
+	size_t len = format_array(NULL, 0, fmt, array, array_size);
+	char *ret;
+
+	ret = kmalloc(len, GFP_KERNEL);
+	if (ret == NULL)
+		return NULL;
+
+	format_array(ret, len, fmt, array, array_size);
+	return ret;
+}
+
+static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
+			      loff_t *ppos)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct array_data *data = inode->i_private;
+	size_t size;
+
+	if (*ppos == 0) {
+		if (file->private_data) {
+			kfree(file->private_data);
+			file->private_data = NULL;
+		}
+
+		file->private_data = format_array_alloc("%u", data->array,
+							      data->elements);
+	}
+
+	size = 0;
+	if (file->private_data)
+		size = strlen(file->private_data);
+
+	return simple_read_from_buffer(buf, len, ppos,
+					file->private_data, size);
+}
+
+static int u32_array_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static const struct file_operations u32_array_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = u32_array_open,
+	.release = u32_array_release,
+	.read	 = u32_array_read,
+	.llseek  = no_llseek,
+};
+
+/**
+ * debugfs_create_u32_array - create a debugfs file that is used to read u32
+ * array.
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @array: u32 array that provides data.
+ * @elements: total number of elements in the array.
+ *
+ * This function creates a file in debugfs with the given name that exports
+ * @array as data. If the @mode variable is so set it can be read from.
+ * Writing is not supported. Seek within the file is also not supported.
+ * Once array is created its size can not be changed.
+ *
+ * The function returns a pointer to dentry on success. If debugfs is not
+ * enabled in the kernel, the value -%ENODEV will be returned.
+ */
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					    struct dentry *parent,
+					    u32 *array, u32 elements)
+{
+	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
+
+	if (data == NULL)
+		return NULL;
+
+	data->array = array;
+	data->elements = elements;
+
+	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
+
 #ifdef CONFIG_HAS_IOMEM
 
 /*

include/linux/debugfs.h

@@ -93,6 +93,10 @@ struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
 int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix);
 
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements);
+
 bool debugfs_initialized(void);
 
 #else
@@ -219,6 +223,13 @@ static inline bool debugfs_initialized(void)
 	return false;
 }
 
+static inline struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 #endif
 
 #endif

include/xen/acpi.h

+/******************************************************************************
+ * acpi.h
+ * acpi file for domain 0 kernel
+ *
+ * Copyright (c) 2011 Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ * Copyright (c) 2011 Yu Ke <ke.yu@intel.com>
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _XEN_ACPI_H
+#define _XEN_ACPI_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_XEN_DOM0
+#include <asm/xen/hypervisor.h>
+#include <xen/xen.h>
+#include <linux/acpi.h>
+
+int xen_acpi_notify_hypervisor_state(u8 sleep_state,
+				     u32 pm1a_cnt, u32 pm1b_cnd);
+
+static inline void xen_acpi_sleep_register(void)
+{
+	if (xen_initial_domain())
+		acpi_os_set_prepare_sleep(
+			&xen_acpi_notify_hypervisor_state);
+}
+#else
+static inline void xen_acpi_sleep_register(void)
+{
+}
+#endif
+
+#endif	/* _XEN_ACPI_H */

include/xen/events.h

@@ -103,6 +103,9 @@ int xen_irq_from_pirq(unsigned pirq);
 /* Return the pirq allocated to the irq. */
 int xen_pirq_from_irq(unsigned irq);
 
+/* Return the irq allocated to the gsi */
+int xen_irq_from_gsi(unsigned gsi);
+
 /* Determine whether to ignore this IRQ if it is passed to a guest. */
 int xen_test_irq_shared(int irq);
 

include/xen/grant_table.h

@@ -46,6 +46,8 @@
 
 #include <xen/features.h>
 
+#define GNTTAB_RESERVED_XENSTORE 1
+
 /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */
 #define NR_GRANT_FRAMES 4
 

include/xen/xenbus_dev.h

@@ -38,4 +38,7 @@
 #define IOCTL_XENBUS_BACKEND_EVTCHN			\
 	_IOC(_IOC_NONE, 'B', 0, 0)
 
+#define IOCTL_XENBUS_BACKEND_SETUP			\
+	_IOC(_IOC_NONE, 'B', 1, 0)
+
 #endif /* __LINUX_XEN_XENBUS_DEV_H__ */