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.

10 files changed, 344 insertions, 212 deletions

diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index ef1db19..c8377fb 100644
--- a/arch/x86/xen/debugfs.c
+++ b/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);
-}
diff --git a/arch/x86/xen/debugfs.h b/arch/x86/xen/debugfs.h
index 78d2549..12ebf33 100644
--- a/arch/x86/xen/debugfs.h
+++ b/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 */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0f5fac..75f33b2 100644
--- a/arch/x86/xen/enlighten.c
+++ b/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. */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3506cd4..3a73785 100644
--- a/arch/x86/xen/mmu.c
+++ b/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;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 1b267e7..ffd08c4 100644
--- a/arch/x86/xen/p2m.c
+++ b/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,
@@ -522,24 +524,66 @@ 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);
+	p2m_init(p2m);
 
-		p2m_top[topidx][mididx] = p2m;
+	p2m_top[topidx][mididx] = p2m;
 
-		/* For save/restore we need to MFN of the P2M saved */
-		
-		mid_mfn_p = p2m_top_mfn_p[topidx];
-		WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
-			"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
-			topidx, mididx);
-		mid_mfn_p[mididx] = virt_to_mfn(p2m);
+	/* For save/restore we need to MFN of the P2M saved */
+
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+		"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+		topidx, mididx);
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
+
+static bool __init early_alloc_p2m(unsigned long pfn)
+{
+	unsigned topidx = p2m_top_index(pfn);
+	unsigned long *mid_mfn_p;
+	unsigned long **mid;
+
+	mid = p2m_top[topidx];
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	if (mid == p2m_mid_missing) {
+		mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+		p2m_mid_init(mid);
+
+		p2m_top[topidx] = mid;
 
+		BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
 	}
-	return idx != 0;
+	/* And the save/restore P2M tables.. */
+	if (mid_mfn_p == p2m_mid_missing_mfn) {
+		mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		p2m_mid_mfn_init(mid_mfn_p);
+
+		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_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)
@@ -559,35 +603,11 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
 		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
 	{
-		unsigned topidx = p2m_top_index(pfn);
-		unsigned long *mid_mfn_p;
-		unsigned long **mid;
-
-		mid = p2m_top[topidx];
-		mid_mfn_p = p2m_top_mfn_p[topidx];
-		if (mid == p2m_mid_missing) {
-			mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-
-			p2m_mid_init(mid);
-
-			p2m_top[topidx] = mid;
-
-			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
-		}
-		/* And the save/restore P2M tables.. */
-		if (mid_mfn_p == p2m_mid_missing_mfn) {
-			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_mfn_init(mid_mfn_p);
-
-			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 */
-		}
+		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)))
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1ba8dff..3ebba07 100644
--- a/arch/x86/xen/setup.c
+++ b/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);
 
-		/* 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);
+		if (release) {
+			/* Make sure pfn exists to start with */
+			if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+				continue;
+			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);
+			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);
@@ -150,20 +256,19 @@ 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;
 		}
 	}
 
-	printk(KERN_INFO "Released %lu pages of unused memory\n", released);
-	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
+	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;
 
@@ -257,9 +364,20 @@ 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
 	 * size is the full initial memory allocation; on highmem it
@@ -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;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3700945..afb250d 100644
--- a/arch/x86/xen/smp.c
+++ b/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);
 }
 
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
new file mode 100644
index 0000000..8981a76
--- /dev/null
+++ b/arch/x86/xen/smp.h
@@ -0,0 +1,12 @@
+#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
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index d69cc6c..83e866d 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -440,12 +440,12 @@ 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,
-				     spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
-	xen_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,
-				     spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
+	debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
+				spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
+	debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
+				spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
+	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+				spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
 
 	return 0;
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 45c0c06..202d4c1 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/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;