Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

16 files changed, 634 insertions, 407 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 5cc821c..26c731a 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -25,8 +25,7 @@ config XEN_PRIVILEGED_GUEST
 
 config XEN_PVHVM
 	def_bool y
-	depends on XEN
-	depends on X86_LOCAL_APIC
+	depends on XEN && PCI && X86_LOCAL_APIC
 
 config XEN_MAX_DOMAIN_MEMORY
        int
@@ -49,11 +48,3 @@ config XEN_DEBUG_FS
 	help
 	  Enable statistics output and various tuning options in debugfs.
 	  Enabling this option may incur a significant performance overhead.
-
-config XEN_DEBUG
-	bool "Enable Xen debug checks"
-	depends on XEN
-	default n
-	help
-	  Enable various WARN_ON checks in the Xen MMU code.
-	  Enabling this option WILL incur a significant performance overhead.
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 17c565d..add2c2d 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -15,8 +15,10 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			grant-table.o suspend.o platform-pci-unplug.o \
 			p2m.o
 
+obj-$(CONFIG_EVENT_TRACING) += trace.o
+
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5525163..1f92865 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type);
 
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int   machine_to_phys_order;
-EXPORT_SYMBOL(machine_to_phys_order);
+unsigned long  machine_to_phys_nr;
+EXPORT_SYMBOL(machine_to_phys_nr);
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void)
 			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
 			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
 	ax = 1;
+	cx = 0;
 	xen_cpuid(&ax, &bx, &cx, &dx);
 
 	xsave_mask =
@@ -341,6 +342,8 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 	struct mmuext_op *op;
 	struct multicall_space mcs = xen_mc_entry(sizeof(*op));
 
+	trace_xen_cpu_set_ldt(addr, entries);
+
 	op = mcs.args;
 	op->cmd = MMUEXT_SET_LDT;
 	op->arg1.linear_addr = (unsigned long)addr;
@@ -496,6 +499,8 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
 	u64 entry = *(u64 *)ptr;
 
+	trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
+
 	preempt_disable();
 
 	xen_mc_flush();
@@ -565,6 +570,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
 	unsigned long p = (unsigned long)&dt[entrynum];
 	unsigned long start, end;
 
+	trace_xen_cpu_write_idt_entry(dt, entrynum, g);
+
 	preempt_disable();
 
 	start = __this_cpu_read(idt_desc.address);
@@ -619,6 +626,8 @@ static void xen_load_idt(const struct desc_ptr *desc)
 	static DEFINE_SPINLOCK(lock);
 	static struct trap_info traps[257];
 
+	trace_xen_cpu_load_idt(desc);
+
 	spin_lock(&lock);
 
 	__get_cpu_var(idt_desc) = *desc;
@@ -637,6 +646,8 @@ static void xen_load_idt(const struct desc_ptr *desc)
 static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
 				const void *desc, int type)
 {
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
 	preempt_disable();
 
 	switch (type) {
@@ -665,6 +676,8 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
 static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 					    const void *desc, int type)
 {
+	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
 	switch (type) {
 	case DESC_LDT:
 	case DESC_TSS:
@@ -684,7 +697,9 @@ static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 static void xen_load_sp0(struct tss_struct *tss,
 			 struct thread_struct *thread)
 {
-	struct multicall_space mcs = xen_mc_entry(0);
+	struct multicall_space mcs;
+
+	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
@@ -937,6 +952,10 @@ static const struct pv_info xen_info __initconst = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+
 	.name = "Xen",
 };
 
@@ -1248,6 +1267,14 @@ asmlinkage void __init xen_start_kernel(void)
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
+		const struct dom0_vga_console_info *info =
+			(void *)((char *)xen_start_info +
+				 xen_start_info->console.dom0.info_off);
+
+		xen_init_vga(info, xen_start_info->console.dom0.info_size);
+		xen_start_info->console.domU.mfn = 0;
+		xen_start_info->console.domU.evtchn = 0;
+
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
@@ -1329,7 +1356,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	int cpu = (long)hcpu;
 	switch (action) {
 	case CPU_UP_PREPARE:
-		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		xen_vcpu_setup(cpu);
 		if (xen_have_vector_callback)
 			xen_init_lock_cpu(cpu);
 		break;
@@ -1359,7 +1386,6 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_smp_init();
 	register_cpu_notifier(&xen_hvm_cpu_notifier);
 	xen_unplug_emulated_devices();
-	have_vcpu_info_placement = 0;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 49ba9b5..5a40d24 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -71,7 +71,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 
 	if (shared == NULL) {
 		struct vm_struct *area =
-			xen_alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
 		BUG_ON(area == NULL);
 		shared = area->addr;
 		*__shared = shared;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index ad54fa1..f4bf8aa 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -48,6 +48,8 @@
 #include <linux/memblock.h>
 #include <linux/seq_file.h>
 
+#include <trace/events/xen.h>
+
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
@@ -194,6 +196,8 @@ void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
 	struct multicall_space mcs;
 	struct mmu_update *u;
 
+	trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
+
 	mcs = xen_mc_entry(sizeof(*u));
 	u = mcs.args;
 
@@ -225,6 +229,24 @@ static void xen_extend_mmu_update(const struct mmu_update *update)
 	*u = *update;
 }
 
+static void xen_extend_mmuext_op(const struct mmuext_op *op)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *u;
+
+	mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
+
+	if (mcs.mc != NULL) {
+		mcs.mc->args[1]++;
+	} else {
+		mcs = __xen_mc_entry(sizeof(*u));
+		MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+	}
+
+	u = mcs.args;
+	*u = *op;
+}
+
 static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 {
 	struct mmu_update u;
@@ -245,6 +267,8 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 
 static void xen_set_pmd(pmd_t *ptr, pmd_t val)
 {
+	trace_xen_mmu_set_pmd(ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -282,22 +306,30 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 	return true;
 }
 
-static void xen_set_pte(pte_t *ptep, pte_t pteval)
+static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
 {
 	if (!xen_batched_set_pte(ptep, pteval))
 		native_set_pte(ptep, pteval);
 }
 
+static void xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+	trace_xen_mmu_set_pte(ptep, pteval);
+	__xen_set_pte(ptep, pteval);
+}
+
 static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval)
 {
-	xen_set_pte(ptep, pteval);
+	trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
+	__xen_set_pte(ptep, pteval);
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
 				 unsigned long addr, pte_t *ptep)
 {
 	/* Just return the pte as-is.  We preserve the bits on commit */
+	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
 	return *ptep;
 }
 
@@ -306,6 +338,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 {
 	struct mmu_update u;
 
+	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
 	xen_mc_batch();
 
 	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
@@ -462,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
 
-#ifdef CONFIG_XEN_DEBUG
-pte_t xen_make_pte_debug(pteval_t pte)
-{
-	phys_addr_t addr = (pte & PTE_PFN_MASK);
-	phys_addr_t other_addr;
-	bool io_page = false;
-	pte_t _pte;
-
-	if (pte & _PAGE_IOMAP)
-		io_page = true;
-
-	_pte = xen_make_pte(pte);
-
-	if (!addr)
-		return _pte;
-
-	if (io_page &&
-	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
-		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
-		WARN_ONCE(addr != other_addr,
-			"0x%lx is using VM_IO, but it is 0x%lx!\n",
-			(unsigned long)addr, (unsigned long)other_addr);
-	} else {
-		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
-		other_addr = (_pte.pte & PTE_PFN_MASK);
-		WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
-			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
-			(unsigned long)addr);
-	}
-
-	return _pte;
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
-#endif
-
 static pgd_t xen_make_pgd(pgdval_t pgd)
 {
 	pgd = pte_pfn_to_mfn(pgd);
@@ -530,6 +528,8 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 
 static void xen_set_pud(pud_t *ptr, pud_t val)
 {
+	trace_xen_mmu_set_pud(ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -543,17 +543,20 @@ static void xen_set_pud(pud_t *ptr, pud_t val)
 #ifdef CONFIG_X86_PAE
 static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
+	trace_xen_mmu_set_pte_atomic(ptep, pte);
 	set_64bit((u64 *)ptep, native_pte_val(pte));
 }
 
 static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	trace_xen_mmu_pte_clear(mm, addr, ptep);
 	if (!xen_batched_set_pte(ptep, native_make_pte(0)))
 		native_pte_clear(mm, addr, ptep);
 }
 
 static void xen_pmd_clear(pmd_t *pmdp)
 {
+	trace_xen_mmu_pmd_clear(pmdp);
 	set_pmd(pmdp, __pmd(0));
 }
 #endif	/* CONFIG_X86_PAE */
@@ -629,6 +632,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 {
 	pgd_t *user_ptr = xen_get_user_pgd(ptr);
 
+	trace_xen_mmu_set_pgd(ptr, user_ptr, val);
+
 	/* If page is not pinned, we can just update the entry
 	   directly */
 	if (!xen_page_pinned(ptr)) {
@@ -788,14 +793,12 @@ static void xen_pte_unlock(void *v)
 
 static void xen_do_pin(unsigned level, unsigned long pfn)
 {
-	struct mmuext_op *op;
-	struct multicall_space mcs;
+	struct mmuext_op op;
 
-	mcs = __xen_mc_entry(sizeof(*op));
-	op = mcs.args;
-	op->cmd = level;
-	op->arg1.mfn = pfn_to_mfn(pfn);
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	op.cmd = level;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+
+	xen_extend_mmuext_op(&op);
 }
 
 static int xen_pin_page(struct mm_struct *mm, struct page *page,
@@ -863,6 +866,8 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
+	trace_xen_mmu_pgd_pin(mm, pgd);
+
 	xen_mc_batch();
 
 	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
@@ -988,6 +993,8 @@ static int xen_unpin_page(struct mm_struct *mm, struct page *page,
 /* Release a pagetables pages back as normal RW */
 static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 {
+	trace_xen_mmu_pgd_unpin(mm, pgd);
+
 	xen_mc_batch();
 
 	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
@@ -1196,6 +1203,8 @@ static void xen_flush_tlb(void)
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb(0);
+
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
@@ -1214,6 +1223,8 @@ static void xen_flush_tlb_single(unsigned long addr)
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb_single(addr);
+
 	preempt_disable();
 
 	mcs = xen_mc_entry(sizeof(*op));
@@ -1240,6 +1251,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	} *args;
 	struct multicall_space mcs;
 
+	trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
 
@@ -1275,10 +1288,11 @@ static void set_current_cr3(void *v)
 
 static void __xen_write_cr3(bool kernel, unsigned long cr3)
 {
-	struct mmuext_op *op;
-	struct multicall_space mcs;
+	struct mmuext_op op;
 	unsigned long mfn;
 
+	trace_xen_mmu_write_cr3(kernel, cr3);
+
 	if (cr3)
 		mfn = pfn_to_mfn(PFN_DOWN(cr3));
 	else
@@ -1286,13 +1300,10 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3)
 
 	WARN_ON(mfn == 0 && kernel);
 
-	mcs = __xen_mc_entry(sizeof(*op));
-
-	op = mcs.args;
-	op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
-	op->arg1.mfn = mfn;
+	op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+	op.arg1.mfn = mfn;
 
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	xen_extend_mmuext_op(&op);
 
 	if (kernel) {
 		percpu_write(xen_cr3, cr3);
@@ -1451,19 +1462,52 @@ static void __init xen_release_pmd_init(unsigned long pfn)
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
+static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct multicall_space mcs;
+	struct mmuext_op *op;
+
+	mcs = __xen_mc_entry(sizeof(*op));
+	op = mcs.args;
+	op->cmd = cmd;
+	op->arg1.mfn = pfn_to_mfn(pfn);
+
+	MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+}
+
+static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	struct multicall_space mcs;
+	unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
+
+	mcs = __xen_mc_entry(0);
+	MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
+				pfn_pte(pfn, prot), 0);
+}
+
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
+static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
+				    unsigned level)
 {
-	struct page *page = pfn_to_page(pfn);
+	bool pinned = PagePinned(virt_to_page(mm->pgd));
+
+	trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
+
+	if (pinned) {
+		struct page *page = pfn_to_page(pfn);
 
-	if (PagePinned(virt_to_page(mm->pgd))) {
 		SetPagePinned(page);
 
 		if (!PageHighMem(page)) {
-			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
+			xen_mc_batch();
+
+			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
+
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
-				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		} else {
 			/* make sure there are no stray mappings of
 			   this page */
@@ -1483,15 +1527,23 @@ static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 }
 
 /* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(unsigned long pfn, unsigned level)
+static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
+	bool pinned = PagePinned(page);
+
+	trace_xen_mmu_release_ptpage(pfn, level, pinned);
 
-	if (PagePinned(page)) {
+	if (pinned) {
 		if (!PageHighMem(page)) {
+			xen_mc_batch();
+
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
-				pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
-			make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+
+			__set_pfn_prot(pfn, PAGE_KERNEL);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		}
 		ClearPagePinned(page);
 	}
@@ -1626,15 +1678,17 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 void __init xen_setup_machphys_mapping(void)
 {
 	struct xen_machphys_mapping mapping;
-	unsigned long machine_to_phys_nr_ents;
 
 	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
 		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
-		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+		machine_to_phys_nr = mapping.max_mfn + 1;
 	} else {
-		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+		machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
 	}
-	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+	WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
+		< machine_to_phys_mapping);
+#endif
 }
 
 #ifdef CONFIG_X86_64
@@ -1825,6 +1879,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # endif
 #else
 	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+	case VVAR_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
@@ -1865,7 +1920,8 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+	    idx == VVAR_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}
@@ -1897,9 +1953,6 @@ void __init xen_ident_map_ISA(void)
 
 static void __init xen_post_allocator_init(void)
 {
-#ifdef CONFIG_XEN_DEBUG
-	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
-#endif
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
@@ -2309,17 +2362,3 @@ out:
 	return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
-
-#ifdef CONFIG_XEN_DEBUG_FS
-static int p2m_dump_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, p2m_dump_show, NULL);
-}
-
-static const struct file_operations p2m_dump_fops = {
-	.open		= p2m_dump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif /* CONFIG_XEN_DEBUG_FS */
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 1b2b73f..0d82003 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -30,12 +30,13 @@
 
 #define MC_BATCH	32
 
-#define MC_DEBUG	1
+#define MC_DEBUG	0
 
 #define MC_ARGS		(MC_BATCH * 16)
 
 
 struct mc_buffer {
+	unsigned mcidx, argidx, cbidx;
 	struct multicall_entry entries[MC_BATCH];
 #if MC_DEBUG
 	struct multicall_entry debug[MC_BATCH];
@@ -46,85 +47,15 @@ struct mc_buffer {
 		void (*fn)(void *);
 		void *data;
 	} callbacks[MC_BATCH];
-	unsigned mcidx, argidx, cbidx;
 };
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
-/* flush reasons 0- slots, 1- args, 2- callbacks */
-enum flush_reasons
-{
-	FL_SLOTS,
-	FL_ARGS,
-	FL_CALLBACKS,
-
-	FL_N_REASONS
-};
-
-#ifdef CONFIG_XEN_DEBUG_FS
-#define NHYPERCALLS	40		/* not really */
-
-static struct {
-	unsigned histo[MC_BATCH+1];
-
-	unsigned issued;
-	unsigned arg_total;
-	unsigned hypercalls;
-	unsigned histo_hypercalls[NHYPERCALLS];
-
-	unsigned flush[FL_N_REASONS];
-} mc_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
-	if (unlikely(zero_stats)) {
-		memset(&mc_stats, 0, sizeof(mc_stats));
-		zero_stats = 0;
-	}
-}
-
-static void mc_add_stats(const struct mc_buffer *mc)
-{
-	int i;
-
-	check_zero();
-
-	mc_stats.issued++;
-	mc_stats.hypercalls += mc->mcidx;
-	mc_stats.arg_total += mc->argidx;
-
-	mc_stats.histo[mc->mcidx]++;
-	for(i = 0; i < mc->mcidx; i++) {
-		unsigned op = mc->entries[i].op;
-		if (op < NHYPERCALLS)
-			mc_stats.histo_hypercalls[op]++;
-	}
-}
-
-static void mc_stats_flush(enum flush_reasons idx)
-{
-	check_zero();
-
-	mc_stats.flush[idx]++;
-}
-
-#else  /* !CONFIG_XEN_DEBUG_FS */
-
-static inline void mc_add_stats(const struct mc_buffer *mc)
-{
-}
-
-static inline void mc_stats_flush(enum flush_reasons idx)
-{
-}
-#endif	/* CONFIG_XEN_DEBUG_FS */
-
 void xen_mc_flush(void)
 {
 	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct multicall_entry *mc;
 	int ret = 0;
 	unsigned long flags;
 	int i;
@@ -135,9 +66,26 @@ void xen_mc_flush(void)
 	   something in the middle */
 	local_irq_save(flags);
 
-	mc_add_stats(b);
+	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
+
+	switch (b->mcidx) {
+	case 0:
+		/* no-op */
+		BUG_ON(b->argidx != 0);
+		break;
+
+	case 1:
+		/* Singleton multicall - bypass multicall machinery
+		   and just do the call directly. */
+		mc = &b->entries[0];
+
+		mc->result = privcmd_call(mc->op,
+					  mc->args[0], mc->args[1], mc->args[2], 
+					  mc->args[3], mc->args[4]);
+		ret = mc->result < 0;
+		break;
 
-	if (b->mcidx) {
+	default:
 #if MC_DEBUG
 		memcpy(b->debug, b->entries,
 		       b->mcidx * sizeof(struct multicall_entry));
@@ -164,11 +112,10 @@ void xen_mc_flush(void)
 			}
 		}
 #endif
+	}
 
-		b->mcidx = 0;
-		b->argidx = 0;
-	} else
-		BUG_ON(b->argidx != 0);
+	b->mcidx = 0;
+	b->argidx = 0;
 
 	for (i = 0; i < b->cbidx; i++) {
 		struct callback *cb = &b->callbacks[i];
@@ -188,18 +135,21 @@ struct multicall_space __xen_mc_entry(size_t args)
 	struct multicall_space ret;
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
+	trace_xen_mc_entry_alloc(args);
+
 	BUG_ON(preemptible());
 	BUG_ON(b->argidx >= MC_ARGS);
 
-	if (b->mcidx == MC_BATCH ||
-	    (argidx + args) >= MC_ARGS) {
-		mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS);
+	if (unlikely(b->mcidx == MC_BATCH ||
+		     (argidx + args) >= MC_ARGS)) {
+		trace_xen_mc_flush_reason((b->mcidx == MC_BATCH) ?
+					  XEN_MC_FL_BATCH : XEN_MC_FL_ARGS);
 		xen_mc_flush();
 		argidx = roundup(b->argidx, sizeof(u64));
 	}
 
 	ret.mc = &b->entries[b->mcidx];
-#ifdef MC_DEBUG
+#if MC_DEBUG
 	b->caller[b->mcidx] = __builtin_return_address(0);
 #endif
 	b->mcidx++;
@@ -218,20 +168,25 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 	BUG_ON(preemptible());
 	BUG_ON(b->argidx >= MC_ARGS);
 
-	if (b->mcidx == 0)
-		return ret;
-
-	if (b->entries[b->mcidx - 1].op != op)
-		return ret;
+	if (unlikely(b->mcidx == 0 ||
+		     b->entries[b->mcidx - 1].op != op)) {
+		trace_xen_mc_extend_args(op, size, XEN_MC_XE_BAD_OP);
+		goto out;
+	}
 
-	if ((b->argidx + size) >= MC_ARGS)
-		return ret;
+	if (unlikely((b->argidx + size) >= MC_ARGS)) {
+		trace_xen_mc_extend_args(op, size, XEN_MC_XE_NO_SPACE);
+		goto out;
+	}
 
 	ret.mc = &b->entries[b->mcidx - 1];
 	ret.args = &b->args[b->argidx];
 	b->argidx += size;
 
 	BUG_ON(b->argidx >= MC_ARGS);
+
+	trace_xen_mc_extend_args(op, size, XEN_MC_XE_OK);
+out:
 	return ret;
 }
 
@@ -241,43 +196,13 @@ void xen_mc_callback(void (*fn)(void *), void *data)
 	struct callback *cb;
 
 	if (b->cbidx == MC_BATCH) {
-		mc_stats_flush(FL_CALLBACKS);
+		trace_xen_mc_flush_reason(XEN_MC_FL_CALLBACK);
 		xen_mc_flush();
 	}
 
+	trace_xen_mc_callback(fn, data);
+
 	cb = &b->callbacks[b->cbidx++];
 	cb->fn = fn;
 	cb->data = data;
 }
-
-#ifdef CONFIG_XEN_DEBUG_FS
-
-static struct dentry *d_mc_debug;
-
-static int __init xen_mc_debugfs(void)
-{
-	struct dentry *d_xen = xen_init_debugfs();
-
-	if (d_xen == NULL)
-		return -ENOMEM;
-
-	d_mc_debug = debugfs_create_dir("multicalls", d_xen);
-
-	debugfs_create_u8("zero_stats", 0644, d_mc_debug, &zero_stats);
-
-	debugfs_create_u32("batches", 0444, d_mc_debug, &mc_stats.issued);
-	debugfs_create_u32("hypercalls", 0444, d_mc_debug, &mc_stats.hypercalls);
-	debugfs_create_u32("arg_total", 0444, d_mc_debug, &mc_stats.arg_total);
-
-	xen_debugfs_create_u32_array("batch_histo", 0444, d_mc_debug,
-				     mc_stats.histo, MC_BATCH);
-	xen_debugfs_create_u32_array("hypercall_histo", 0444, d_mc_debug,
-				     mc_stats.histo_hypercalls, NHYPERCALLS);
-	xen_debugfs_create_u32_array("flush_reasons", 0444, d_mc_debug,
-				     mc_stats.flush, FL_N_REASONS);
-
-	return 0;
-}
-fs_initcall(xen_mc_debugfs);
-
-#endif	/* CONFIG_XEN_DEBUG_FS */
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 4ec8035..dee79b7 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -1,6 +1,8 @@
 #ifndef _XEN_MULTICALLS_H
 #define _XEN_MULTICALLS_H
 
+#include <trace/events/xen.h>
+
 #include "xen-ops.h"
 
 /* Multicalls */
@@ -20,8 +22,10 @@ DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
 static inline void xen_mc_batch(void)
 {
 	unsigned long flags;
+
 	/* need to disable interrupts until this entry is complete */
 	local_irq_save(flags);
+	trace_xen_mc_batch(paravirt_get_lazy_mode());
 	__this_cpu_write(xen_mc_irq_flags, flags);
 }
 
@@ -37,6 +41,8 @@ void xen_mc_flush(void);
 /* Issue a multicall if we're not in a lazy mode */
 static inline void xen_mc_issue(unsigned mode)
 {
+	trace_xen_mc_issue(mode);
+
 	if ((paravirt_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 58efeb9..1b267e7 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,7 +161,9 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/grant_table.h>
 
+#include "multicalls.h"
 #include "xen-ops.h"
 
 static void __init m2p_override_init(void);
@@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn)
 }
 
 /* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
+int m2p_add_override(unsigned long mfn, struct page *page,
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
 	unsigned long pfn;
@@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
 	}
-
-	page->private = mfn;
+	WARN_ON(PagePrivate(page));
+	SetPagePrivate(page);
+	set_page_private(page, mfn);
 	page->index = pfn_to_mfn(pfn);
 
 	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
 		return -ENOMEM;
 
-	if (clear_pte && !PageHighMem(page))
-		/* Just zap old mapping for now */
-		pte_clear(&init_mm, address, ptep);
+	if (kmap_op != NULL) {
+		if (!PageHighMem(page)) {
+			struct multicall_space mcs =
+				xen_mc_entry(sizeof(*kmap_op));
+
+			MULTI_grant_table_op(mcs.mc,
+					GNTTABOP_map_grant_ref, kmap_op, 1);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+		}
+		/* let's use dev_bus_addr to record the old mfn instead */
+		kmap_op->dev_bus_addr = page->index;
+		page->index = (unsigned long) kmap_op;
+	}
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
@@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
-	set_phys_to_machine(pfn, page->index);
+	WARN_ON(!PagePrivate(page));
+	ClearPagePrivate(page);
 
-	if (clear_pte && !PageHighMem(page))
-		set_pte_at(&init_mm, address, ptep,
-				pfn_pte(pfn, PAGE_KERNEL));
-		/* No tlb flush necessary because the caller already
-		 * left the pte unmapped. */
+	if (clear_pte) {
+		struct gnttab_map_grant_ref *map_op =
+			(struct gnttab_map_grant_ref *) page->index;
+		set_phys_to_machine(pfn, map_op->dev_bus_addr);
+		if (!PageHighMem(page)) {
+			struct multicall_space mcs;
+			struct gnttab_unmap_grant_ref *unmap_op;
+
+			/*
+			 * It might be that we queued all the m2p grant table
+			 * hypercalls in a multicall, then m2p_remove_override
+			 * get called before the multicall has actually been
+			 * issued. In this case handle is going to -1 because
+			 * it hasn't been modified yet.
+			 */
+			if (map_op->handle == -1)
+				xen_mc_flush();
+			/*
+			 * Now if map_op->handle is negative it means that the
+			 * hypercall actually returned an error.
+			 */
+			if (map_op->handle == GNTST_general_error) {
+				printk(KERN_WARNING "m2p_remove_override: "
+						"pfn %lx mfn %lx, failed to modify kernel mappings",
+						pfn, mfn);
+				return -1;
+			}
+
+			mcs = xen_mc_entry(
+					sizeof(struct gnttab_unmap_grant_ref));
+			unmap_op = mcs.args;
+			unmap_op->host_addr = map_op->host_addr;
+			unmap_op->handle = map_op->handle;
+			unmap_op->dev_bus_addr = 0;
+
+			MULTI_grant_table_op(mcs.mc,
+					GNTTABOP_unmap_grant_ref, unmap_op, 1);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+			set_pte_at(&init_mm, address, ptep,
+					pfn_pte(pfn, PAGE_KERNEL));
+			__flush_tlb_single(address);
+			map_op->host_addr = 0;
+		}
+	} else
+		set_phys_to_machine(pfn, page->index);
 
 	return 0;
 }
@@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn)
 	spin_lock_irqsave(&m2p_override_lock, flags);
 
 	list_for_each_entry(p, bucket, lru) {
-		if (p->private == mfn) {
+		if (page_private(p) == mfn) {
 			ret = p;
 			break;
 		}
@@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
 EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
 
 #ifdef CONFIG_XEN_DEBUG_FS
-
-int p2m_dump_show(struct seq_file *m, void *v)
+#include <linux/debugfs.h>
+#include "debugfs.h"
+static int p2m_dump_show(struct seq_file *m, void *v)
 {
 	static const char * const level_name[] = { "top", "middle",
-						"entry", "abnormal" };
-	static const char * const type_name[] = { "identity", "missing",
-						"pfn", "abnormal"};
+						"entry", "abnormal", "error"};
 #define TYPE_IDENTITY 0
 #define TYPE_MISSING 1
 #define TYPE_PFN 2
 #define TYPE_UNKNOWN 3
+	static const char * const type_name[] = {
+				[TYPE_IDENTITY] = "identity",
+				[TYPE_MISSING] = "missing",
+				[TYPE_PFN] = "pfn",
+				[TYPE_UNKNOWN] = "abnormal"};
 	unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
 	unsigned int uninitialized_var(prev_level);
 	unsigned int uninitialized_var(prev_type);
@@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v)
 #undef TYPE_PFN
 #undef TYPE_UNKNOWN
 }
-#endif
+
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+	.open		= p2m_dump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *d_mmu_debug;
+
+static int __init xen_p2m_debugfs(void)
+{
+	struct dentry *d_xen = xen_init_debugfs();
+
+	if (d_xen == NULL)
+		return -ENOMEM;
+
+	d_mmu_debug = debugfs_create_dir("mmu", d_xen);
+
+	debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
+	return 0;
+}
+fs_initcall(xen_p2m_debugfs);
+#endif /* CONFIG_XEN_DEBUG_FS */
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 25c52f9..ffcf261 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
 #ifdef CONFIG_XEN_PVHVM
 static int xen_emul_unplug;
 
-static int __init check_platform_magic(void)
+static int check_platform_magic(void)
 {
 	short magic;
 	char protocol;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 73daaf7..f5e1362 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/memblock.h>
+#include <linux/cpuidle.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -36,7 +37,10 @@ extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
 
 /* Amount of extra memory space we add to the e820 ranges */
-phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
+struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
+
+/* Number of pages released from the initial allocation. */
+unsigned long xen_released_pages;
 
 /* 
  * The maximum amount of extra memory compared to the base size.  The
@@ -50,50 +54,47 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
  */
 #define EXTRA_MEM_RATIO		(10)
 
-static void __init xen_add_extra_mem(unsigned long pages)
+static void __init xen_add_extra_mem(u64 start, u64 size)
 {
 	unsigned long pfn;
+	int i;
 
-	u64 size = (u64)pages * PAGE_SIZE;
-	u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
-
-	if (!pages)
-		return;
-
-	e820_add_region(extra_start, size, E820_RAM);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-
-	memblock_reserve(extra_start, size);
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		/* Add new region. */
+		if (xen_extra_mem[i].size == 0) {
+			xen_extra_mem[i].start = start;
+			xen_extra_mem[i].size  = size;
+			break;
+		}
+		/* Append to existing region. */
+		if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
+			xen_extra_mem[i].size += size;
+			break;
+		}
+	}
+	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
+		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
 
-	xen_extra_mem_size += size;
+	memblock_reserve(start, size);
 
-	xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+	xen_max_p2m_pfn = PFN_DOWN(start + size);
 
-	for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
+	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 }
 
-static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
-					      phys_addr_t end_addr)
+static unsigned long __init xen_release_chunk(unsigned long start,
+					      unsigned long end)
 {
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
 		.extent_order = 0,
 		.domid        = DOMID_SELF
 	};
-	unsigned long start, end;
 	unsigned long len = 0;
 	unsigned long pfn;
 	int ret;
 
-	start = PFN_UP(start_addr);
-	end = PFN_DOWN(end_addr);
-
-	if (end <= start)
-		return 0;
-
-	printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ",
-	       start, end);
 	for(pfn = start; pfn < end; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
 
@@ -106,100 +107,104 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
 
 		ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
 					   &reservation);
-		WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
-		     start, end, ret);
+		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
 		if (ret == 1) {
 			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 			len++;
 		}
 	}
-	printk(KERN_CONT "%ld pages freed\n", len);
+	printk(KERN_INFO "Freeing  %lx-%lx pfn range: %lu pages freed\n",
+	       start, end, len);
 
 	return len;
 }
 
-static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
-						     const struct e820map *e820)
+static unsigned long __init xen_set_identity_and_release(
+	const struct e820entry *list, size_t map_size, unsigned long nr_pages)
 {
-	phys_addr_t max_addr = PFN_PHYS(max_pfn);
-	phys_addr_t last_end = ISA_END_ADDRESS;
+	phys_addr_t start = 0;
 	unsigned long released = 0;
+	unsigned long identity = 0;
+	const struct e820entry *entry;
 	int i;
 
-	/* Free any unused memory above the low 1Mbyte. */
-	for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
-		phys_addr_t end = e820->map[i].addr;
-		end = min(max_addr, end);
+	/*
+	 * Combine non-RAM regions and gaps until a RAM region (or the
+	 * end of the map) is reached, then set the 1:1 map and
+	 * release the pages (if available) in those non-RAM regions.
+	 *
+	 * The combined non-RAM regions are rounded to a whole number
+	 * of pages so any partial pages are accessible via the 1:1
+	 * mapping.  This is needed for some BIOSes that put (for
+	 * example) the DMI tables in a reserved region that begins on
+	 * a non-page boundary.
+	 */
+	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);
 
-		if (last_end < end)
-			released += xen_release_chunk(last_end, end);
-		last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
+			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));
+
+				identity += set_phys_range_identity(
+					start_pfn, end_pfn);
+			}
+			start = end;
+		}
 	}
 
-	if (last_end < max_addr)
-		released += xen_release_chunk(last_end, max_addr);
+	printk(KERN_INFO "Released %lu pages of unused memory\n", released);
+	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
 
-	printk(KERN_INFO "released %ld pages of unused memory\n", released);
 	return released;
 }
 
-static unsigned long __init xen_set_identity(const struct e820entry *list,
-					     ssize_t map_size)
+static unsigned long __init xen_get_max_pages(void)
 {
-	phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS;
-	phys_addr_t start_pci = last;
-	const struct e820entry *entry;
-	unsigned long identity = 0;
-	int i;
-
-	for (i = 0, entry = list; i < map_size; i++, entry++) {
-		phys_addr_t start = entry->addr;
-		phys_addr_t end = start + entry->size;
-
-		if (start < last)
-			start = last;
-
-		if (end <= start)
-			continue;
+	unsigned long max_pages = MAX_DOMAIN_PAGES;
+	domid_t domid = DOMID_SELF;
+	int ret;
 
-		/* Skip over the 1MB region. */
-		if (last > end)
-			continue;
+	ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+	if (ret > 0)
+		max_pages = ret;
+	return min(max_pages, MAX_DOMAIN_PAGES);
+}
 
-		if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) {
-			if (start > start_pci)
-				identity += set_phys_range_identity(
-						PFN_UP(start_pci), PFN_DOWN(start));
+static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
+{
+	u64 end = start + size;
 
-			/* Without saving 'last' we would gooble RAM too
-			 * at the end of the loop. */
-			last = end;
-			start_pci = end;
-			continue;
-		}
-		start_pci = min(start, start_pci);
-		last = end;
+	/* Align RAM regions to page boundaries. */
+	if (type == E820_RAM) {
+		start = PAGE_ALIGN(start);
+		end &= ~((u64)PAGE_SIZE - 1);
 	}
-	if (last > start_pci)
-		identity += set_phys_range_identity(
-					PFN_UP(start_pci), PFN_DOWN(last));
-	return identity;
+
+	e820_add_region(start, end - start, type);
 }
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
 char * __init xen_memory_setup(void)
 {
 	static struct e820entry map[E820MAX] __initdata;
-	static struct e820entry map_raw[E820MAX] __initdata;
 
 	unsigned long max_pfn = xen_start_info->nr_pages;
 	unsigned long long mem_end;
 	int rc;
 	struct xen_memory_map memmap;
+	unsigned long max_pages;
 	unsigned long extra_pages = 0;
-	unsigned long extra_limit;
-	unsigned long identity_pages = 0;
 	int i;
 	int op;
 
@@ -225,58 +230,65 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
-	memcpy(map_raw, map, sizeof(map));
-	e820.nr_map = 0;
-	xen_extra_mem_start = mem_end;
-	for (i = 0; i < memmap.nr_entries; i++) {
-		unsigned long long end;
-
-		/* Guard against non-page aligned E820 entries. */
-		if (map[i].type == E820_RAM)
-			map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE;
-
-		end = map[i].addr + map[i].size;
-		if (map[i].type == E820_RAM && end > mem_end) {
-			/* RAM off the end - may be partially included */
-			u64 delta = min(map[i].size, end - mem_end);
-
-			map[i].size -= delta;
-			end -= delta;
-
-			extra_pages += PFN_DOWN(delta);
-			/*
-			 * Set RAM below 4GB that is not for us to be unusable.
-			 * This prevents "System RAM" address space from being
-			 * used as potential resource for I/O address (happens
-			 * when 'allocate_resource' is called).
-			 */
-			if (delta &&
-				(xen_initial_domain() && end < 0x100000000ULL))
-				e820_add_region(end, delta, E820_UNUSABLE);
+	/* Make sure the Xen-supplied memory map is well-ordered. */
+	sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
+
+	max_pages = xen_get_max_pages();
+	if (max_pages > max_pfn)
+		extra_pages += max_pages - max_pfn;
+
+	/*
+	 * Set P2M for all non-RAM pages and E820 gaps to be identity
+	 * type PFNs.  Any RAM pages that would be made inaccesible by
+	 * this are first released.
+	 */
+	xen_released_pages = xen_set_identity_and_release(
+		map, memmap.nr_entries, max_pfn);
+	extra_pages += xen_released_pages;
+
+	/*
+	 * 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
+	 * is limited to the max size of lowmem, so that it doesn't
+	 * get completely filled.
+	 *
+	 * In principle there could be a problem in lowmem systems if
+	 * the initial memory is also very large with respect to
+	 * lowmem, but we won't try to deal with that here.
+	 */
+	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;
+		u64 size = map[i].size;
+		u32 type = map[i].type;
+
+		if (type == E820_RAM) {
+			if (addr < mem_end) {
+				size = min(size, mem_end - addr);
+			} else if (extra_pages) {
+				size = min(size, (u64)extra_pages * PAGE_SIZE);
+				extra_pages -= size / PAGE_SIZE;
+				xen_add_extra_mem(addr, size);
+			} else
+				type = E820_UNUSABLE;
 		}
 
-		if (map[i].size > 0 && end > xen_extra_mem_start)
-			xen_extra_mem_start = end;
+		xen_align_and_add_e820_region(addr, size, type);
 
-		/* Add region if any remains */
-		if (map[i].size > 0)
-			e820_add_region(map[i].addr, map[i].size, map[i].type);
+		map[i].addr += size;
+		map[i].size -= size;
+		if (map[i].size == 0)
+			i++;
 	}
-	/* Align the balloon area so that max_low_pfn does not get set
-	 * to be at the _end_ of the PCI gap at the far end (fee01000).
-	 * Note that xen_extra_mem_start gets set in the loop above to be
-	 * past the last E820 region. */
-	if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
-		xen_extra_mem_start = (1ULL<<32);
 
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
 	 * reserve ISA memory anyway because too many things poke
 	 * about in there.
-	 *
-	 * In Dom0, the host E820 information can leave gaps in the
-	 * ISA range, which would cause us to release those pages.  To
-	 * avoid this, we unconditionally reserve them here.
 	 */
 	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
 			E820_RESERVED);
@@ -292,36 +304,6 @@ char * __init xen_memory_setup(void)
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
-	extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
-
-	/*
-	 * 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
-	 * is limited to the max size of lowmem, so that it doesn't
-	 * get completely filled.
-	 *
-	 * In principle there could be a problem in lowmem systems if
-	 * the initial memory is also very large with respect to
-	 * lowmem, but we won't try to deal with that here.
-	 */
-	extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
-			  max_pfn + extra_pages);
-
-	if (extra_limit >= max_pfn)
-		extra_pages = extra_limit - max_pfn;
-	else
-		extra_pages = 0;
-
-	xen_add_extra_mem(extra_pages);
-
-	/*
-	 * Set P2M for all non-RAM pages and E820 gaps to be identity
-	 * type PFNs. We supply it with the non-sanitized version
-	 * of the E820.
-	 */
-	identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
-	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
 	return "Xen";
 }
 
@@ -425,7 +407,7 @@ void __init xen_arch_setup(void)
 #ifdef CONFIG_X86_32
 	boot_cpu_data.hlt_works_ok = 1;
 #endif
-	pm_idle = default_idle;
+	disable_cpuidle();
 	boot_option_idle_override = IDLE_HALT;
 
 	fiddle_vdso();
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b4533a8..041d4fe 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -32,6 +32,7 @@
 #include <xen/page.h>
 #include <xen/events.h>
 
+#include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
 
@@ -207,6 +208,15 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	unsigned cpu;
 	unsigned int i;
 
+	if (skip_ioapic_setup) {
+		char *m = (max_cpus == 0) ?
+			"The nosmp parameter is incompatible with Xen; " \
+			"use Xen dom0_max_vcpus=1 parameter" :
+			"The noapic parameter is incompatible with Xen";
+
+		xen_raw_printk(m);
+		panic(m);
+	}
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
@@ -521,10 +531,7 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	native_smp_prepare_cpus(max_cpus);
 	WARN_ON(xen_smp_intr_init(0));
 
-	if (!xen_have_vector_callback)
-		return;
 	xen_init_lock_cpu(0);
-	xen_init_spinlocks();
 }
 
 static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
@@ -546,6 +553,8 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
+	if (!xen_have_vector_callback)
+		return;
 	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;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5158c50..0296a95 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -168,9 +168,10 @@ cycle_t xen_clocksource_read(void)
         struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
 
-	src = &get_cpu_var(xen_vcpu)->time;
+	preempt_disable_notrace();
+	src = &__get_cpu_var(xen_vcpu)->time;
 	ret = pvclock_clocksource_read(src);
-	put_cpu_var(xen_vcpu);
+	preempt_enable_notrace();
 	return ret;
 }
 
@@ -200,8 +201,22 @@ static unsigned long xen_get_wallclock(void)
 
 static int xen_set_wallclock(unsigned long now)
 {
+	struct xen_platform_op op;
+	int rc;
+
 	/* do nothing for domU */
-	return -1;
+	if (!xen_initial_domain())
+		return -1;
+
+	op.cmd = XENPF_settime;
+	op.u.settime.secs = now;
+	op.u.settime.nsecs = 0;
+	op.u.settime.system_time = xen_clocksource_read();
+
+	rc = HYPERVISOR_dom0_op(&op);
+	WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now);
+
+	return rc;
 }
 
 static struct clocksource xen_clocksource __read_mostly = {
diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c
new file mode 100644
index 0000000..520022d
--- /dev/null
+++ b/arch/x86/xen/trace.c
@@ -0,0 +1,62 @@
+#include <linux/ftrace.h>
+#include <xen/interface/xen.h>
+
+#define N(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),
+};
+#undef N
+
+static const char *xen_hypercall_name(unsigned op)
+{
+	if (op < ARRAY_SIZE(xen_hypercall_names) && xen_hypercall_names[op] != NULL)
+		return xen_hypercall_names[op];
+
+	return "";
+}
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/xen.h>
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
new file mode 100644
index 0000000..1cd7f4d
--- /dev/null
+++ b/arch/x86/xen/vga.c
@@ -0,0 +1,67 @@
+#include <linux/screen_info.h>
+#include <linux/init.h>
+
+#include <asm/bootparam.h>
+#include <asm/setup.h>
+
+#include <xen/interface/xen.h>
+
+#include "xen-ops.h"
+
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+{
+	struct screen_info *screen_info = &boot_params.screen_info;
+
+	/* This is drawn from a dump from vgacon:startup in
+	 * standard Linux. */
+	screen_info->orig_video_mode = 3;
+	screen_info->orig_video_isVGA = 1;
+	screen_info->orig_video_lines = 25;
+	screen_info->orig_video_cols = 80;
+	screen_info->orig_video_ega_bx = 3;
+	screen_info->orig_video_points = 16;
+	screen_info->orig_y = screen_info->orig_video_lines - 1;
+
+	switch (info->video_type) {
+	case XEN_VGATYPE_TEXT_MODE_3:
+		if (size < offsetof(struct dom0_vga_console_info, u.text_mode_3)
+		    + sizeof(info->u.text_mode_3))
+			break;
+		screen_info->orig_video_lines = info->u.text_mode_3.rows;
+		screen_info->orig_video_cols = info->u.text_mode_3.columns;
+		screen_info->orig_x = info->u.text_mode_3.cursor_x;
+		screen_info->orig_y = info->u.text_mode_3.cursor_y;
+		screen_info->orig_video_points =
+			info->u.text_mode_3.font_height;
+		break;
+
+	case XEN_VGATYPE_VESA_LFB:
+		if (size < offsetof(struct dom0_vga_console_info,
+				    u.vesa_lfb.gbl_caps))
+			break;
+		screen_info->orig_video_isVGA = VIDEO_TYPE_VLFB;
+		screen_info->lfb_width = info->u.vesa_lfb.width;
+		screen_info->lfb_height = info->u.vesa_lfb.height;
+		screen_info->lfb_depth = info->u.vesa_lfb.bits_per_pixel;
+		screen_info->lfb_base = info->u.vesa_lfb.lfb_base;
+		screen_info->lfb_size = info->u.vesa_lfb.lfb_size;
+		screen_info->lfb_linelength = info->u.vesa_lfb.bytes_per_line;
+		screen_info->red_size = info->u.vesa_lfb.red_size;
+		screen_info->red_pos = info->u.vesa_lfb.red_pos;
+		screen_info->green_size = info->u.vesa_lfb.green_size;
+		screen_info->green_pos = info->u.vesa_lfb.green_pos;
+		screen_info->blue_size = info->u.vesa_lfb.blue_size;
+		screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
+		screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
+		screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.gbl_caps)
+		    + sizeof(info->u.vesa_lfb.gbl_caps))
+			screen_info->capabilities = info->u.vesa_lfb.gbl_caps;
+		if (size >= offsetof(struct dom0_vga_console_info,
+				     u.vesa_lfb.mode_attrs)
+		    + sizeof(info->u.vesa_lfb.mode_attrs))
+			screen_info->vesa_attributes = info->u.vesa_lfb.mode_attrs;
+		break;
+	}
+}
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 22a2093..b040b0e 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -113,11 +113,13 @@ xen_iret_start_crit:
 
 	/*
 	 * If there's something pending, mask events again so we can
-	 * jump back into xen_hypervisor_callback
+	 * jump back into xen_hypervisor_callback. Otherwise do not
+	 * touch XEN_vcpu_info_mask.
 	 */
-	sete XEN_vcpu_info_mask(%eax)
+	jne 1f
+	movb $1, XEN_vcpu_info_mask(%eax)
 
-	popl %eax
+1:	popl %eax
 
 	/*
 	 * From this point on the registers are restored and the stack
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 97dfdc8..b095739 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -88,6 +88,17 @@ static inline void xen_uninit_lock_cpu(int cpu)
 }
 #endif
 
+struct dom0_vga_console_info;
+
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#else
+static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
+				       size_t size)
+{
+}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\