7 files changed, 338 insertions, 349 deletions

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 7005ced5d1ad..70e060ad879a 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -7,6 +7,7 @@
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
 #include "xen-ops.h"
+#include "smp.h"
 
 static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 {
@@ -28,7 +29,186 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 	return 0xfd;
 }
 
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+	WARN_ON(1);
+	return x;
+}
+
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+	return ((x)>>24) & 0xFFu;
+}
+
+static u32 xen_apic_read(u32 reg)
+{
+	struct xen_platform_op op = {
+		.cmd = XENPF_get_cpuinfo,
+		.interface_version = XENPF_INTERFACE_VERSION,
+		.u.pcpu_info.xen_cpuid = 0,
+	};
+	int ret = 0;
+
+	/* Shouldn't need this as APIC is turned off for PV, and we only
+	 * get called on the bootup processor. But just in case. */
+	if (!xen_initial_domain() || smp_processor_id())
+		return 0;
+
+	if (reg == APIC_LVR)
+		return 0x10;
+#ifdef CONFIG_X86_32
+	if (reg == APIC_LDR)
+		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
+#endif
+	if (reg != APIC_ID)
+		return 0;
+
+	ret = HYPERVISOR_dom0_op(&op);
+	if (ret)
+		return 0;
+
+	return op.u.pcpu_info.apic_id << 24;
+}
+
+static void xen_apic_write(u32 reg, u32 val)
+{
+	/* Warn to see if there's any stray references */
+	WARN(1,"register: %x, value: %x\n", reg, val);
+}
+
+static u64 xen_apic_icr_read(void)
+{
+	return 0;
+}
+
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+	/* Warn to see if there's any stray references */
+	WARN_ON(1);
+}
+
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+        return 0;
+}
+
+static int xen_apic_probe_pv(void)
+{
+	if (xen_pv_domain())
+		return 1;
+
+	return 0;
+}
+
+static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return xen_pv_domain();
+}
+
+static int xen_id_always_valid(int apicid)
+{
+	return 1;
+}
+
+static int xen_id_always_registered(void)
+{
+	return 1;
+}
+
+static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+	return initial_apic_id >> index_msb;
+}
+
+#ifdef CONFIG_X86_32
+static int xen_x86_32_early_logical_apicid(int cpu)
+{
+	/* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */
+	return 1 << cpu;
+}
+#endif
+
+static void xen_noop(void)
+{
+}
+
+static void xen_silent_inquire(int apicid)
+{
+}
+
+static struct apic xen_pv_apic = {
+	.name 				= "Xen PV",
+	.probe 				= xen_apic_probe_pv,
+	.acpi_madt_oem_check		= xen_madt_oem_check,
+	.apic_id_valid 			= xen_id_always_valid,
+	.apic_id_registered 		= xen_id_always_registered,
+
+	/* .irq_delivery_mode - used in native_compose_msi_msg only */
+	/* .irq_dest_mode     - used in native_compose_msi_msg only */
+
+	.target_cpus			= default_target_cpus,
+	.disable_esr			= 0,
+	/* .dest_logical      -  default_send_IPI_ use it but we use our own. */
+	.check_apicid_used		= default_check_apicid_used, /* Used on 32-bit */
+
+	.vector_allocation_domain	= flat_vector_allocation_domain,
+	.init_apic_ldr			= xen_noop, /* setup_local_APIC calls it */
+
+	.ioapic_phys_id_map		= default_ioapic_phys_id_map, /* Used on 32-bit */
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= physid_set_mask_of_physid, /* Used on 32-bit */
+	.check_phys_apicid_present	= default_check_phys_apicid_present, /* smp_sanity_check needs it */
+	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */
+
+	.get_apic_id 			= xen_get_apic_id,
+	.set_apic_id 			= xen_set_apic_id, /* Can be NULL on 32-bit. */
+	.apic_id_mask			= 0xFF << 24, /* Used by verify_local_APIC. Match with what xen_get_apic_id does. */
+
+	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
+
+#ifdef CONFIG_SMP
+	.send_IPI_mask 			= xen_send_IPI_mask,
+	.send_IPI_mask_allbutself 	= xen_send_IPI_mask_allbutself,
+	.send_IPI_allbutself 		= xen_send_IPI_allbutself,
+	.send_IPI_all 			= xen_send_IPI_all,
+	.send_IPI_self 			= xen_send_IPI_self,
+#endif
+	/* .wait_for_init_deassert- used  by AP bootup - smp_callin which we don't use */
+	.inquire_remote_apic		= xen_silent_inquire,
+
+	.read				= xen_apic_read,
+	.write				= xen_apic_write,
+	.eoi_write			= xen_apic_write,
+
+	.icr_read 			= xen_apic_icr_read,
+	.icr_write 			= xen_apic_icr_write,
+	.wait_icr_idle 			= xen_noop,
+	.safe_wait_icr_idle 		= xen_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+	/* generic_processor_info and setup_local_APIC. */
+	.x86_32_early_logical_apicid	= xen_x86_32_early_logical_apicid,
+#endif
+};
+
+static void __init xen_apic_check(void)
+{
+	if (apic == &xen_pv_apic)
+		return;
+
+	pr_info("Switched APIC routing from %s to %s.\n", apic->name,
+		xen_pv_apic.name);
+	apic = &xen_pv_apic;
+}
 void __init xen_init_apic(void)
 {
 	x86_io_apic_ops.read = xen_io_apic_read;
+	/* On PV guests the APIC CPUID bit is disabled so none of the
+	 * routines end up executing. */
+	if (!xen_initial_domain())
+		apic = &xen_pv_apic;
+
+	x86_platform.apic_post_init = xen_apic_check;
 }
+apic_driver(xen_pv_apic);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 3797b6b31f95..fe969ac1c65e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -928,92 +928,6 @@ static void xen_io_delay(void)
 {
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-static unsigned long xen_set_apic_id(unsigned int x)
-{
-	WARN_ON(1);
-	return x;
-}
-static unsigned int xen_get_apic_id(unsigned long x)
-{
-	return ((x)>>24) & 0xFFu;
-}
-static u32 xen_apic_read(u32 reg)
-{
-	struct xen_platform_op op = {
-		.cmd = XENPF_get_cpuinfo,
-		.interface_version = XENPF_INTERFACE_VERSION,
-		.u.pcpu_info.xen_cpuid = 0,
-	};
-	int ret = 0;
-
-	/* Shouldn't need this as APIC is turned off for PV, and we only
-	 * get called on the bootup processor. But just in case. */
-	if (!xen_initial_domain() || smp_processor_id())
-		return 0;
-
-	if (reg == APIC_LVR)
-		return 0x10;
-
-	if (reg != APIC_ID)
-		return 0;
-
-	ret = HYPERVISOR_dom0_op(&op);
-	if (ret)
-		return 0;
-
-	return op.u.pcpu_info.apic_id << 24;
-}
-
-static void xen_apic_write(u32 reg, u32 val)
-{
-	/* Warn to see if there's any stray references */
-	WARN_ON(1);
-}
-
-static u64 xen_apic_icr_read(void)
-{
-	return 0;
-}
-
-static void xen_apic_icr_write(u32 low, u32 id)
-{
-	/* Warn to see if there's any stray references */
-	WARN_ON(1);
-}
-
-static void xen_apic_wait_icr_idle(void)
-{
-        return;
-}
-
-static u32 xen_safe_apic_wait_icr_idle(void)
-{
-        return 0;
-}
-
-static void set_xen_basic_apic_ops(void)
-{
-	apic->read = xen_apic_read;
-	apic->write = xen_apic_write;
-	apic->icr_read = xen_apic_icr_read;
-	apic->icr_write = xen_apic_icr_write;
-	apic->wait_icr_idle = xen_apic_wait_icr_idle;
-	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
-
 static void xen_clts(void)
 {
 	struct multicall_space mcs;
@@ -1620,7 +1534,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/*
 	 * set up the basic apic ops.
 	 */
-	set_xen_basic_apic_ops();
+	xen_init_apic();
 #endif
 
 	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
@@ -1733,8 +1647,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		if (HYPERVISOR_dom0_op(&op) == 0)
 			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
 
-		xen_init_apic();
-
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 
@@ -1849,6 +1761,9 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 
 static void __init xen_hvm_guest_init(void)
 {
+	if (xen_pv_domain())
+		return;
+
 	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
@@ -1864,6 +1779,7 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
 }
+#endif
 
 static bool xen_nopv = false;
 static __init int xen_parse_nopv(char *arg)
@@ -1873,14 +1789,11 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
-static uint32_t __init xen_hvm_platform(void)
+static uint32_t __init xen_platform(void)
 {
 	if (xen_nopv)
 		return 0;
 
-	if (xen_pv_domain())
-		return 0;
-
 	return xen_cpuid_base();
 }
 
@@ -1898,11 +1811,19 @@ bool xen_hvm_need_lapic(void)
 }
 EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
-const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
-	.name			= "Xen HVM",
-	.detect			= xen_hvm_platform,
+static void xen_set_cpu_features(struct cpuinfo_x86 *c)
+{
+	if (xen_pv_domain())
+		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+const struct hypervisor_x86 x86_hyper_xen = {
+	.name			= "Xen",
+	.detect			= xen_platform,
+#ifdef CONFIG_XEN_PVHVM
 	.init_platform		= xen_hvm_guest_init,
+#endif
 	.x2apic_available	= xen_x2apic_para_available,
+	.set_cpu_features       = xen_set_cpu_features,
 };
-EXPORT_SYMBOL(x86_hyper_xen_hvm);
-#endif
+EXPORT_SYMBOL(x86_hyper_xen);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index adca9e2b6553..dd151b2045b0 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -502,7 +502,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 __visible pudval_t xen_pud_val(pud_t pud)
 {
 	return pte_mfn_to_pfn(pud.pud);
@@ -589,7 +589,7 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
-#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
 /*
  * (Yet another) pagetable walker.  This one is intended for pinning a
@@ -1628,7 +1628,7 @@ static void xen_release_pmd(unsigned long pfn)
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -2046,7 +2046,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	pv_mmu_ops.set_pgd = xen_set_pgd;
 #endif
 
@@ -2056,7 +2056,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
@@ -2122,14 +2122,14 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#if PAGETABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS == 4
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
 	.set_pgd = xen_set_pgd_hyper,
 
 	.alloc_pud = xen_alloc_pmd_init,
 	.release_pud = xen_release_pmd_init,
-#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
@@ -2436,99 +2436,11 @@ void __init xen_hvm_init_mmu_ops(void)
 }
 #endif
 
-#ifdef CONFIG_XEN_PVH
-/*
- * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user
- * space creating new guest on pvh dom0 and needing to map domU pages.
- */
-static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn,
-			    unsigned int domid)
-{
-	int rc, err = 0;
-	xen_pfn_t gpfn = lpfn;
-	xen_ulong_t idx = fgfn;
-
-	struct xen_add_to_physmap_range xatp = {
-		.domid = DOMID_SELF,
-		.foreign_domid = domid,
-		.size = 1,
-		.space = XENMAPSPACE_gmfn_foreign,
-	};
-	set_xen_guest_handle(xatp.idxs, &idx);
-	set_xen_guest_handle(xatp.gpfns, &gpfn);
-	set_xen_guest_handle(xatp.errs, &err);
-
-	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
-	if (rc < 0)
-		return rc;
-	return err;
-}
-
-static int xlate_remove_from_p2m(unsigned long spfn, int count)
-{
-	struct xen_remove_from_physmap xrp;
-	int i, rc;
-
-	for (i = 0; i < count; i++) {
-		xrp.domid = DOMID_SELF;
-		xrp.gpfn = spfn+i;
-		rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
-		if (rc)
-			break;
-	}
-	return rc;
-}
-
-struct xlate_remap_data {
-	unsigned long fgfn; /* foreign domain's gfn */
-	pgprot_t prot;
-	domid_t  domid;
-	int index;
-	struct page **pages;
-};
-
-static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
-			    void *data)
-{
-	int rc;
-	struct xlate_remap_data *remap = data;
-	unsigned long pfn = page_to_pfn(remap->pages[remap->index++]);
-	pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot));
-
-	rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid);
-	if (rc)
-		return rc;
-	native_set_pte(ptep, pteval);
-
-	return 0;
-}
-
-static int xlate_remap_gfn_range(struct vm_area_struct *vma,
-				 unsigned long addr, unsigned long mfn,
-				 int nr, pgprot_t prot, unsigned domid,
-				 struct page **pages)
-{
-	int err;
-	struct xlate_remap_data pvhdata;
-
-	BUG_ON(!pages);
-
-	pvhdata.fgfn = mfn;
-	pvhdata.prot = prot;
-	pvhdata.domid = domid;
-	pvhdata.index = 0;
-	pvhdata.pages = pages;
-	err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT,
-				  xlate_map_pte_fn, &pvhdata);
-	flush_tlb_all();
-	return err;
-}
-#endif
-
 #define REMAP_BATCH_SIZE 16
 
 struct remap_data {
-	unsigned long mfn;
+	xen_pfn_t *mfn;
+	bool contiguous;
 	pgprot_t prot;
 	struct mmu_update *mmu_update;
 };
@@ -2537,7 +2449,14 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 				 unsigned long addr, void *data)
 {
 	struct remap_data *rmd = data;
-	pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot));
+	pte_t pte = pte_mkspecial(mfn_pte(*rmd->mfn, rmd->prot));
+
+	/* If we have a contigious range, just update the mfn itself,
+	   else update pointer to be "next mfn". */
+	if (rmd->contiguous)
+		(*rmd->mfn)++;
+	else
+		rmd->mfn++;
 
 	rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
 	rmd->mmu_update->val = pte_val_ma(pte);
@@ -2546,26 +2465,26 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 	return 0;
 }
 
-int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
-			       unsigned long addr,
-			       xen_pfn_t mfn, int nr,
-			       pgprot_t prot, unsigned domid,
-			       struct page **pages)
-
+static int do_remap_mfn(struct vm_area_struct *vma,
+			unsigned long addr,
+			xen_pfn_t *mfn, int nr,
+			int *err_ptr, pgprot_t prot,
+			unsigned domid,
+			struct page **pages)
 {
+	int err = 0;
 	struct remap_data rmd;
 	struct mmu_update mmu_update[REMAP_BATCH_SIZE];
-	int batch;
 	unsigned long range;
-	int err = 0;
+	int mapped = 0;
 
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
 
 	if (xen_feature(XENFEAT_auto_translated_physmap)) {
 #ifdef CONFIG_XEN_PVH
 		/* We need to update the local page tables and the xen HAP */
-		return xlate_remap_gfn_range(vma, addr, mfn, nr, prot,
-					     domid, pages);
+		return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr,
+						 prot, domid, pages);
 #else
 		return -EINVAL;
 #endif
@@ -2573,9 +2492,15 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 
 	rmd.mfn = mfn;
 	rmd.prot = prot;
+	/* We use the err_ptr to indicate if there we are doing a contigious
+	 * mapping or a discontigious mapping. */
+	rmd.contiguous = !err_ptr;
 
 	while (nr) {
-		batch = min(REMAP_BATCH_SIZE, nr);
+		int index = 0;
+		int done = 0;
+		int batch = min(REMAP_BATCH_SIZE, nr);
+		int batch_left = batch;
 		range = (unsigned long)batch << PAGE_SHIFT;
 
 		rmd.mmu_update = mmu_update;
@@ -2584,23 +2509,72 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 		if (err)
 			goto out;
 
-		err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid);
-		if (err < 0)
-			goto out;
+		/* We record the error for each page that gives an error, but
+		 * continue mapping until the whole set is done */
+		do {
+			int i;
+
+			err = HYPERVISOR_mmu_update(&mmu_update[index],
+						    batch_left, &done, domid);
+
+			/*
+			 * @err_ptr may be the same buffer as @mfn, so
+			 * only clear it after each chunk of @mfn is
+			 * used.
+			 */
+			if (err_ptr) {
+				for (i = index; i < index + done; i++)
+					err_ptr[i] = 0;
+			}
+			if (err < 0) {
+				if (!err_ptr)
+					goto out;
+				err_ptr[i] = err;
+				done++; /* Skip failed frame. */
+			} else
+				mapped += done;
+			batch_left -= done;
+			index += done;
+		} while (batch_left);
 
 		nr -= batch;
 		addr += range;
+		if (err_ptr)
+			err_ptr += batch;
 	}
-
-	err = 0;
 out:
 
 	xen_flush_tlb_all();
 
-	return err;
+	return err < 0 ? err : mapped;
+}
+
+int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
+			       unsigned long addr,
+			       xen_pfn_t mfn, int nr,
+			       pgprot_t prot, unsigned domid,
+			       struct page **pages)
+{
+	return do_remap_mfn(vma, addr, &mfn, nr, NULL, prot, domid, pages);
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
 
+int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
+			       unsigned long addr,
+			       xen_pfn_t *mfn, int nr,
+			       int *err_ptr, pgprot_t prot,
+			       unsigned domid, struct page **pages)
+{
+	/* We BUG_ON because it's a programmer error to pass a NULL err_ptr,
+	 * and the consequences later is quite hard to detect what the actual
+	 * cause of "wrong memory was mapped in".
+	 */
+	BUG_ON(err_ptr == NULL);
+	return do_remap_mfn(vma, addr, mfn, nr, err_ptr, prot, domid, pages);
+}
+EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array);
+
+
 /* Returns: 0 success */
 int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 			       int numpgs, struct page **pages)
@@ -2609,22 +2583,7 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 		return 0;
 
 #ifdef CONFIG_XEN_PVH
-	while (numpgs--) {
-		/*
-		 * The mmu has already cleaned up the process mmu
-		 * resources at this point (lookup_address will return
-		 * NULL).
-		 */
-		unsigned long pfn = page_to_pfn(pages[numpgs]);
-
-		xlate_remove_from_p2m(pfn, 1);
-	}
-	/*
-	 * We don't need to flush tlbs because as part of
-	 * xlate_remove_from_p2m, the hypervisor will do tlb flushes
-	 * after removing the p2m entries from the EPT/NPT
-	 */
-	return 0;
+	return xen_xlate_unmap_gfn_range(vma, numpgs, pages);
 #else
 	return -EINVAL;
 #endif
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7413ee3706d0..86484384492e 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -90,14 +90,10 @@ static void cpu_bringup(void)
 
 	set_cpu_online(cpu, true);
 
-	this_cpu_write(cpu_state, CPU_ONLINE);
-
-	wmb();
+	cpu_set_state_online(cpu);  /* Implies full memory barrier. */
 
 	/* We can take interrupts now: we're officially "up". */
 	local_irq_enable();
-
-	wmb();			/* make sure everything is out */
 }
 
 /*
@@ -451,7 +447,13 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	xen_setup_timer(cpu);
 	xen_init_lock_cpu(cpu);
 
-	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+	/*
+	 * PV VCPUs are always successfully taken down (see 'while' loop
+	 * in xen_cpu_die()), so -EBUSY is an error.
+	 */
+	rc = cpu_check_up_prepare(cpu);
+	if (rc)
+		return rc;
 
 	/* make sure interrupts start blocked */
 	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
@@ -467,10 +469,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL);
 	BUG_ON(rc);
 
-	while(per_cpu(cpu_state, cpu) != CPU_ONLINE) {
+	while (cpu_report_state(cpu) != CPU_ONLINE)
 		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
-		barrier();
-	}
 
 	return 0;
 }
@@ -499,11 +499,11 @@ static void xen_cpu_die(unsigned int cpu)
 		schedule_timeout(HZ/10);
 	}
 
-	cpu_die_common(cpu);
-
-	xen_smp_intr_free(cpu);
-	xen_uninit_lock_cpu(cpu);
-	xen_teardown_timer(cpu);
+	if (common_cpu_die(cpu) == 0) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+		xen_teardown_timer(cpu);
+	}
 }
 
 static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
@@ -735,6 +735,16 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc;
+
+	/*
+	 * This can happen if CPU was offlined earlier and
+	 * offlining timed out in common_cpu_die().
+	 */
+	if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+	}
+
 	/*
 	 * xen_smp_intr_init() needs to run before native_cpu_up()
 	 * so that IPI vectors are set up on the booting CPU before
@@ -756,12 +766,6 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return rc;
 }
 
-static void xen_hvm_cpu_die(unsigned int cpu)
-{
-	xen_cpu_die(cpu);
-	native_cpu_die(cpu);
-}
-
 void __init xen_hvm_smp_init(void)
 {
 	if (!xen_have_vector_callback)
@@ -769,7 +773,7 @@ void __init xen_hvm_smp_init(void)
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.cpu_up = xen_hvm_cpu_up;
-	smp_ops.cpu_die = xen_hvm_cpu_die;
+	smp_ops.cpu_die = xen_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
 	smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index d9497698645a..53b4c0811f4f 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -88,7 +88,17 @@ static void xen_vcpu_notify_restore(void *data)
 	tick_resume_local();
 }
 
+static void xen_vcpu_notify_suspend(void *data)
+{
+	tick_suspend_local();
+}
+
 void xen_arch_resume(void)
 {
 	on_each_cpu(xen_vcpu_notify_restore, NULL, 1);
 }
+
+void xen_arch_suspend(void)
+{
+	on_each_cpu(xen_vcpu_notify_suspend, NULL, 1);
+}
diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c
index 520022d1a181..a702ec2f5931 100644
--- a/arch/x86/xen/trace.c
+++ b/arch/x86/xen/trace.c
@@ -1,54 +1,12 @@
 #include <linux/ftrace.h>
 #include <xen/interface/xen.h>
+#include <xen/interface/xen-mca.h>
 
-#define N(x)	[__HYPERVISOR_##x] = "("#x")"
+#define HYPERCALL(x)	[__HYPERVISOR_##x] = "("#x")",
 static const char *xen_hypercall_names[] = {
-	N(set_trap_table),
-	N(mmu_update),
-	N(set_gdt),
-	N(stack_switch),
-	N(set_callbacks),
-	N(fpu_taskswitch),
-	N(sched_op_compat),
-	N(dom0_op),
-	N(set_debugreg),
-	N(get_debugreg),
-	N(update_descriptor),
-	N(memory_op),
-	N(multicall),
-	N(update_va_mapping),
-	N(set_timer_op),
-	N(event_channel_op_compat),
-	N(xen_version),
-	N(console_io),
-	N(physdev_op_compat),
-	N(grant_table_op),
-	N(vm_assist),
-	N(update_va_mapping_otherdomain),
-	N(iret),
-	N(vcpu_op),
-	N(set_segment_base),
-	N(mmuext_op),
-	N(acm_op),
-	N(nmi_op),
-	N(sched_op),
-	N(callback_op),
-	N(xenoprof_op),
-	N(event_channel_op),
-	N(physdev_op),
-	N(hvm_op),
-
-/* Architecture-specific hypercall definitions. */
-	N(arch_0),
-	N(arch_1),
-	N(arch_2),
-	N(arch_3),
-	N(arch_4),
-	N(arch_5),
-	N(arch_6),
-	N(arch_7),
+#include <asm/xen-hypercalls.h>
 };
-#undef N
+#undef HYPERCALL
 
 static const char *xen_hypercall_name(unsigned op)
 {
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 674b222544b7..8afdfccf6086 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -12,6 +12,8 @@
 
 #include <xen/interface/elfnote.h>
 #include <xen/interface/features.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
 #ifdef CONFIG_XEN_PVH
@@ -85,59 +87,14 @@ ENTRY(xen_pvh_early_cpu_init)
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
-#define NEXT_HYPERCALL(x) \
-	ENTRY(xen_hypercall_##x) \
-	.skip 32
-
-NEXT_HYPERCALL(set_trap_table)
-NEXT_HYPERCALL(mmu_update)
-NEXT_HYPERCALL(set_gdt)
-NEXT_HYPERCALL(stack_switch)
-NEXT_HYPERCALL(set_callbacks)
-NEXT_HYPERCALL(fpu_taskswitch)
-NEXT_HYPERCALL(sched_op_compat)
-NEXT_HYPERCALL(platform_op)
-NEXT_HYPERCALL(set_debugreg)
-NEXT_HYPERCALL(get_debugreg)
-NEXT_HYPERCALL(update_descriptor)
-NEXT_HYPERCALL(ni)
-NEXT_HYPERCALL(memory_op)
-NEXT_HYPERCALL(multicall)
-NEXT_HYPERCALL(update_va_mapping)
-NEXT_HYPERCALL(set_timer_op)
-NEXT_HYPERCALL(event_channel_op_compat)
-NEXT_HYPERCALL(xen_version)
-NEXT_HYPERCALL(console_io)
-NEXT_HYPERCALL(physdev_op_compat)
-NEXT_HYPERCALL(grant_table_op)
-NEXT_HYPERCALL(vm_assist)
-NEXT_HYPERCALL(update_va_mapping_otherdomain)
-NEXT_HYPERCALL(iret)
-NEXT_HYPERCALL(vcpu_op)
-NEXT_HYPERCALL(set_segment_base)
-NEXT_HYPERCALL(mmuext_op)
-NEXT_HYPERCALL(xsm_op)
-NEXT_HYPERCALL(nmi_op)
-NEXT_HYPERCALL(sched_op)
-NEXT_HYPERCALL(callback_op)
-NEXT_HYPERCALL(xenoprof_op)
-NEXT_HYPERCALL(event_channel_op)
-NEXT_HYPERCALL(physdev_op)
-NEXT_HYPERCALL(hvm_op)
-NEXT_HYPERCALL(sysctl)
-NEXT_HYPERCALL(domctl)
-NEXT_HYPERCALL(kexec_op)
-NEXT_HYPERCALL(tmem_op) /* 38 */
-ENTRY(xen_hypercall_rsvr)
-	.skip 320
-NEXT_HYPERCALL(mca) /* 48 */
-NEXT_HYPERCALL(arch_1)
-NEXT_HYPERCALL(arch_2)
-NEXT_HYPERCALL(arch_3)
-NEXT_HYPERCALL(arch_4)
-NEXT_HYPERCALL(arch_5)
-NEXT_HYPERCALL(arch_6)
-	.balign PAGE_SIZE
+	.skip PAGE_SIZE
+
+#define HYPERCALL(n) \
+	.equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
+	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
+#include <asm/xen-hypercalls.h>
+#undef HYPERCALL
+
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")