Merge branch 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (42 commits)
  xen: cache cr0 value to avoid trap'n'emulate for read_cr0
  xen/x86-64: clean up warnings about IST-using traps
  xen/x86-64: fix breakpoints and hardware watchpoints
  xen: reserve Xen start_info rather than e820 reserving
  xen: add FIX_TEXT_POKE to fixmap
  lguest: update lazy mmu changes to match lguest's use of kvm hypercalls
  xen: honour VCPU availability on boot
  xen: add "capabilities" file
  xen: drop kexec bits from /sys/hypervisor since kexec isn't implemented yet
  xen/sys/hypervisor: change writable_pt to features
  xen: add /sys/hypervisor support
  xen/xenbus: export xenbus_dev_changed
  xen: use device model for suspending xenbus devices
  xen: remove suspend_cancel hook
  xen/dev-evtchn: clean up locking in evtchn
  xen: export ioctl headers to userspace
  xen: add /dev/xen/evtchn driver
  xen: add irq_from_evtchn
  xen: clean up gate trap/interrupt constants
  xen: set _PAGE_NX in __supported_pte_mask before pagetable construction
  ...

37 files changed, 1281 insertions, 174 deletions

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a53da004e08e..4fb37c8a0832 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -56,6 +56,7 @@ struct desc_ptr;
 struct tss_struct;
 struct mm_struct;
 struct desc_struct;
+struct task_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -203,7 +204,8 @@ struct pv_cpu_ops {
 
         void (*swapgs)(void);
 
-        struct pv_lazy_ops lazy_mode;
+        void (*start_context_switch)(struct task_struct *prev);
+        void (*end_context_switch)(struct task_struct *next);
 };
 
 struct pv_irq_ops {
@@ -1399,25 +1401,23 @@ enum paravirt_lazy_mode {
 };
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
 
-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define  __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
 {
-        PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+        PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
 }
 
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
 {
-        PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+        PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
 }
 
-void arch_flush_lazy_cpu_mode(void);
-
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3f8d09d94eb3..18ef7ebf2631 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -81,6 +81,8 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 #define pte_val(x)      native_pte_val(x)
 #define __pte(x)        native_make_pte(x)
 
+#define arch_end_context_switch(prev)   do {} while(0)
+
 #endif  /* CONFIG_PARAVIRT */
 
 /*
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index a4737dddfd58..64cf2d24fad1 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -48,9 +48,15 @@
 #endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE        0
-#define NEED_MSR        (1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE        0
+#else
+#define NEED_PSE        (1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE        (1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR        (1<<(X86_FEATURE_MSR & 31))
 #define NEED_FXSR       (1<<(X86_FEATURE_FXSR & 31))
 #define NEED_XMM        (1<<(X86_FEATURE_XMM & 31))
 #define NEED_XMM2       (1<<(X86_FEATURE_XMM2 & 31))
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8820a73ae090..602c769fc98c 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -94,7 +94,8 @@ struct thread_info {
 #define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
-#define TIF_SYSCALL_FTRACE      27      /* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES    27      /* task is updating the mmu lazily */
+#define TIF_SYSCALL_FTRACE      28      /* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME      (1 << TIF_NOTIFY_RESUME)
@@ -116,6 +117,7 @@ struct thread_info {
 #define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
+#define _TIF_LAZY_MMU_UPDATES   (1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_FTRACE     (1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index cbfdc26b1460..bfd74c032fca 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -14,6 +14,9 @@ asmlinkage void divide_error(void);
 asmlinkage void debug(void);
 asmlinkage void nmi(void);
 asmlinkage void int3(void);
+asmlinkage void xen_debug(void);
+asmlinkage void xen_int3(void);
+asmlinkage void xen_stack_segment(void);
 asmlinkage void overflow(void);
 asmlinkage void bounds(void);
 asmlinkage void invalid_op(void);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 38946c6e8433..bb01ce080b80 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1379,6 +1379,11 @@ END(xen_failsafe_callback)
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
 paranoiderrorentry stack_segment do_stack_segment
+#ifdef CONFIG_XEN
+zeroentry xen_debug do_debug
+zeroentry xen_int3 do_int3
+errorentry xen_stack_segment do_stack_segment
+#endif
 errorentry general_protection do_general_protection
 errorentry page_fault do_page_fault
 #ifdef CONFIG_X86_MCE
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33019ddb56b4..6551dedee20c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -195,7 +195,7 @@ static void kvm_leave_lazy_mmu(void)
         struct kvm_para_state *state = kvm_para_state();
 
         mmu_queue_flush(state);
-        paravirt_leave_lazy(paravirt_get_lazy_mode());
+        paravirt_leave_lazy_mmu();
         state->mode = paravirt_get_lazy_mode();
 }
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9faf43bea336..70ec9b951d76 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -248,18 +248,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LA
 
 static inline void enter_lazy(enum paravirt_lazy_mode mode)
 {
-        BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-        BUG_ON(preemptible());
+        BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
 
-        __get_cpu_var(paravirt_lazy_mode) = mode;
+        percpu_write(paravirt_lazy_mode, mode);
 }
 
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
 {
-        BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
-        BUG_ON(preemptible());
+        BUG_ON(percpu_read(paravirt_lazy_mode) != mode);
 
-        __get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+        percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 void paravirt_enter_lazy_mmu(void)
@@ -269,22 +267,36 @@ void paravirt_enter_lazy_mmu(void)
 
 void paravirt_leave_lazy_mmu(void)
 {
-        paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+        leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
-void paravirt_enter_lazy_cpu(void)
+void paravirt_start_context_switch(struct task_struct *prev)
 {
+        BUG_ON(preemptible());
+
+        if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+                arch_leave_lazy_mmu_mode();
+                set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+        }
         enter_lazy(PARAVIRT_LAZY_CPU);
 }
 
-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
 {
-        paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+        BUG_ON(preemptible());
+
+        leave_lazy(PARAVIRT_LAZY_CPU);
+
+        if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+                arch_enter_lazy_mmu_mode();
 }
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 {
-        return __get_cpu_var(paravirt_lazy_mode);
+        if (in_interrupt())
+                return PARAVIRT_LAZY_NONE;
+
+        return percpu_read(paravirt_lazy_mode);
 }
 
 void arch_flush_lazy_mmu_mode(void)
@@ -292,7 +304,6 @@ void arch_flush_lazy_mmu_mode(void)
         preempt_disable();
 
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-                WARN_ON(preempt_count() == 1);
                 arch_leave_lazy_mmu_mode();
                 arch_enter_lazy_mmu_mode();
         }
@@ -300,19 +311,6 @@ void arch_flush_lazy_mmu_mode(void)
         preempt_enable();
 }
 
-void arch_flush_lazy_cpu_mode(void)
-{
-        preempt_disable();
-
-        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-                WARN_ON(preempt_count() == 1);
-                arch_leave_lazy_cpu_mode();
-                arch_enter_lazy_cpu_mode();
-        }
-
-        preempt_enable();
-}
-
 struct pv_info pv_info = {
         .name = "bare hardware",
         .paravirt_enabled = 0,
@@ -404,10 +402,8 @@ struct pv_cpu_ops pv_cpu_ops = {
         .set_iopl_mask = native_set_iopl_mask,
         .io_delay = native_io_delay,
 
-        .lazy_mode = {
-                .enter = paravirt_nop,
-                .leave = paravirt_nop,
-        },
+        .start_context_switch = paravirt_nop,
+        .end_context_switch = paravirt_nop,
 };
 
 struct pv_apic_ops pv_apic_ops = {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 56d50b7d71df..c60924b5d123 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -404,7 +404,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          * done before math_state_restore, so the TS bit is up
          * to date.
          */
-        arch_leave_lazy_cpu_mode();
+        arch_end_context_switch(next_p);
 
         /* If the task has used fpu the last 5 timeslices, just do a full
          * restore of the math state immediately to avoid the trap; the
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9d6b20e6cd80..45f010fb2e20 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -425,7 +425,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          * done before math_state_restore, so the TS bit is up
          * to date.
          */
-        arch_leave_lazy_cpu_mode();
+        arch_end_context_switch(next_p);
 
         /*
          * Switch FS and GS.
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95deb9f2211e..b263423fbe2a 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -462,22 +462,28 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
 {
-        paravirt_enter_lazy_cpu();
+        paravirt_start_context_switch(prev);
         vmi_ops.set_lazy_mode(2);
 }
 
+static void vmi_end_context_switch(struct task_struct *next)
+{
+        vmi_ops.set_lazy_mode(0);
+        paravirt_end_context_switch(next);
+}
+
 static void vmi_enter_lazy_mmu(void)
 {
         paravirt_enter_lazy_mmu();
         vmi_ops.set_lazy_mode(1);
 }
 
-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
 {
-        paravirt_leave_lazy(paravirt_get_lazy_mode());
         vmi_ops.set_lazy_mode(0);
+        paravirt_leave_lazy_mmu();
 }
 
 static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -711,14 +717,14 @@ static inline int __init activate_vmi(void)
         para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
         para_fill(pv_cpu_ops.io_delay, IODelay);
 
-        para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+        para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
                   set_lazy_mode, SetLazyMode);
-        para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+        para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
                   set_lazy_mode, SetLazyMode);
 
         para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
                   set_lazy_mode, SetLazyMode);
-        para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+        para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
                   set_lazy_mode, SetLazyMode);
 
         /* user and kernel flush are just handled with different flags to FlushTLB */
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index ef4205c1a7a5..4e0c26559395 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -167,10 +167,16 @@ static void lazy_hcall3(unsigned long call,
 
 /* When lazy mode is turned off reset the per-cpu lazy mode variable and then
  * issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
 {
-        paravirt_leave_lazy(paravirt_get_lazy_mode());
         kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+        kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        paravirt_end_context_switch(next);
 }
 
 /*G:033
@@ -1054,8 +1060,8 @@ __init void lguest_init(void)
         pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
         pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
         pv_cpu_ops.wbinvd = lguest_wbinvd;
-        pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
-        pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+        pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+        pv_cpu_ops.end_context_switch = lguest_end_context_switch;
 
         /* pagetable management */
         pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1068,7 +1074,7 @@ __init void lguest_init(void)
         pv_mmu_ops.read_cr2 = lguest_read_cr2;
         pv_mmu_ops.read_cr3 = lguest_read_cr3;
         pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
-        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
         pv_mmu_ops.pte_update = lguest_pte_update;
         pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b9ca6d767dbb..5ec7ae366615 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -201,12 +201,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
         if (!pmd_present(*pmd_k))
                 return NULL;
 
-        if (!pmd_present(*pmd)) {
+        if (!pmd_present(*pmd))
                 set_pmd(pmd, *pmd_k);
-                arch_flush_lazy_mmu_mode();
-        } else {
+        else
                 BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-        }
 
         return pmd_k;
 }
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 8126e8d1a2a4..58f621e81919 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -44,7 +44,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
         vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
         BUG_ON(!pte_none(*(kmap_pte-idx)));
         set_pte(kmap_pte-idx, mk_pte(page, prot));
-        arch_flush_lazy_mmu_mode();
 
         return (void *)vaddr;
 }
@@ -74,7 +73,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
         }
 
-        arch_flush_lazy_mmu_mode();
         pagefault_enable();
 }
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 8056545e2d39..fe6f84ca121e 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -82,7 +82,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
         if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
                 kpte_clear_flush(kmap_pte-idx, vaddr);
 
-        arch_flush_lazy_mmu_mode();
         pagefault_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e17efed088c5..6ce9518fe2ac 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -839,13 +839,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
         vm_unmap_aliases();
 
-        /*
-         * If we're called with lazy mmu updates enabled, the
-         * in-memory pte state may be stale.  Flush pending updates to
-         * bring them up to date.
-         */
-        arch_flush_lazy_mmu_mode();
-
         cpa.vaddr = addr;
         cpa.pages = pages;
         cpa.numpages = numpages;
@@ -890,13 +883,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
         } else
                 cpa_flush_all(cache);
 
-        /*
-         * If we've been called with lazy mmu updates enabled, then
-         * make sure that everything gets flushed out before we
-         * return.
-         */
-        arch_flush_lazy_mmu_mode();
-
 out:
         return ret;
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f09e8c36ee80..0a1700a2be9c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
+#include <linux/kprobes.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -44,6 +45,7 @@
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/msr-index.h>
+#include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
@@ -240,10 +242,10 @@ static unsigned long xen_get_debugreg(int reg)
         return HYPERVISOR_get_debugreg(reg);
 }
 
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
 {
-        paravirt_leave_lazy(paravirt_get_lazy_mode());
         xen_mc_flush();
+        paravirt_end_context_switch(next);
 }
 
 static unsigned long xen_store_tr(void)
@@ -428,11 +430,44 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
                             struct trap_info *info)
 {
+        unsigned long addr;
+
         if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
                 return 0;
 
         info->vector = vector;
-        info->address = gate_offset(*val);
+
+        addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+        /*
+         * Look for known traps using IST, and substitute them
+         * appropriately.  The debugger ones are the only ones we care
+         * about.  Xen will handle faults like double_fault and
+         * machine_check, so we should never see them.  Warn if
+         * there's an unexpected IST-using fault handler.
+         */
+        if (addr == (unsigned long)debug)
+                addr = (unsigned long)xen_debug;
+        else if (addr == (unsigned long)int3)
+                addr = (unsigned long)xen_int3;
+        else if (addr == (unsigned long)stack_segment)
+                addr = (unsigned long)xen_stack_segment;
+        else if (addr == (unsigned long)double_fault ||
+                 addr == (unsigned long)nmi) {
+                /* Don't need to handle these */
+                return 0;
+#ifdef CONFIG_X86_MCE
+        } else if (addr == (unsigned long)machine_check) {
+                return 0;
+#endif
+        } else {
+                /* Some other trap using IST? */
+                if (WARN_ON(val->ist != 0))
+                        return 0;
+        }
+#endif  /* CONFIG_X86_64 */
+        info->address = addr;
+
         info->cs = gate_segment(*val);
         info->flags = val->dpl;
         /* interrupt gates clear IF */
@@ -623,10 +658,26 @@ static void xen_clts(void)
         xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+        unsigned long cr0 = percpu_read(xen_cr0_value);
+
+        if (unlikely(cr0 == 0)) {
+                cr0 = native_read_cr0();
+                percpu_write(xen_cr0_value, cr0);
+        }
+
+        return cr0;
+}
+
 static void xen_write_cr0(unsigned long cr0)
 {
         struct multicall_space mcs;
 
+        percpu_write(xen_cr0_value, cr0);
+
         /* Only pay attention to cr0.TS; everything else is
            ignored. */
         mcs = xen_mc_entry(0);
@@ -812,7 +863,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 
         .clts = xen_clts,
 
-        .read_cr0 = native_read_cr0,
+        .read_cr0 = xen_read_cr0,
         .write_cr0 = xen_write_cr0,
 
         .read_cr4 = native_read_cr4,
@@ -860,10 +911,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
         /* Xen takes care of %gs when switching to usermode for us */
         .swapgs = paravirt_nop,
 
-        .lazy_mode = {
-                .enter = paravirt_enter_lazy_cpu,
-                .leave = xen_leave_lazy,
-        },
+        .start_context_switch = paravirt_start_context_switch,
+        .end_context_switch = xen_end_context_switch,
 };
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fba55b1a4021..4ceb28581652 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -452,10 +452,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
                     pte_t *ptep, pte_t pteval)
 {
-        /* updates to init_mm may be done without lock */
-        if (mm == &init_mm)
-                preempt_disable();
-
         ADD_STATS(set_pte_at, 1);
 //      ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
         ADD_STATS(set_pte_at_current, mm == current->mm);
@@ -476,9 +472,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
         }
         xen_set_pte(ptep, pteval);
 
-out:
-        if (mm == &init_mm)
-                preempt_enable();
+out:    return;
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
@@ -1152,10 +1146,8 @@ static void drop_other_mm_ref(void *info)
 
         /* If this cpu still has a stale cr3 reference, then make sure
            it has been flushed. */
-        if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+        if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
                 load_cr3(swapper_pg_dir);
-                arch_flush_lazy_cpu_mode();
-        }
 }
 
 static void xen_drop_mm_ref(struct mm_struct *mm)
@@ -1168,7 +1160,6 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
                         load_cr3(swapper_pg_dir);
                 else
                         leave_mm(smp_processor_id());
-                arch_flush_lazy_cpu_mode();
         }
 
         /* Get the "official" set of cpus referring to our pagetable. */
@@ -1876,6 +1867,14 @@ __init void xen_post_allocator_init(void)
         xen_mark_init_mm_pinned();
 }
 
+static void xen_leave_lazy_mmu(void)
+{
+        preempt_disable();
+        xen_mc_flush();
+        paravirt_leave_lazy_mmu();
+        preempt_enable();
+}
+
 const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .pagetable_setup_start = xen_pagetable_setup_start,
         .pagetable_setup_done = xen_pagetable_setup_done,
@@ -1949,7 +1948,7 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
         .lazy_mode = {
                 .enter = paravirt_enter_lazy_mmu,
-                .leave = xen_leave_lazy,
+                .leave = xen_leave_lazy_mmu,
         },
 
         .set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 15c6c68db6a2..ad0047f47cd4 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -61,9 +61,9 @@ char * __init xen_memory_setup(void)
          *  - xen_start_info
          * See comment above "struct start_info" in <xen/interface/xen.h>
          */
-        e820_add_region(__pa(xen_start_info->mfn_list),
-                        xen_start_info->pt_base - xen_start_info->mfn_list,
-                        E820_RESERVED);
+        reserve_early(__pa(xen_start_info->mfn_list),
+                      __pa(xen_start_info->pt_base),
+                        "XEN START INFO");
 
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ca6596b05d53..22494fd4c9b5 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,7 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 
-void xen_leave_lazy(void);
 void xen_post_allocator_init(void);
 
 char * __init xen_memory_setup(void);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 8ac9cddac575..cab100acf983 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -18,6 +18,16 @@ config XEN_SCRUB_PAGES
           secure, but slightly less efficient.
           If in doubt, say yes.
 
+config XEN_DEV_EVTCHN
+        tristate "Xen /dev/xen/evtchn device"
+        depends on XEN
+        default y
+        help
+          The evtchn driver allows a userspace process to triger event
+          channels and to receive notification of an event channel
+          firing.
+          If in doubt, say yes.
+
 config XENFS
         tristate "Xen filesystem"
         depends on XEN
@@ -41,3 +51,13 @@ config XEN_COMPAT_XENFS
          a xen platform.
          If in doubt, say yes.
 
+config XEN_SYS_HYPERVISOR
+       bool "Create xen entries under /sys/hypervisor"
+       depends on XEN && SYSFS
+       select SYS_HYPERVISOR
+       default y
+       help
+         Create entries under /sys/hypervisor describing the Xen
+         hypervisor environment.  When running native or in another
+         virtual environment, /sys/hypervisor will still be present,
+         but will have no xen contents.
\ No newline at end of file
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index ff8accc9e103..ec2a39b1e26f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -4,4 +4,6 @@ obj-y	+= xenbus/
 obj-$(CONFIG_HOTPLUG_CPU)       += cpu_hotplug.o
 obj-$(CONFIG_XEN_XENCOMM)       += xencomm.o
 obj-$(CONFIG_XEN_BALLOON)       += balloon.o
-obj-$(CONFIG_XENFS)             += xenfs/
\ No newline at end of file
+obj-$(CONFIG_XEN_DEV_EVTCHN)    += evtchn.o
+obj-$(CONFIG_XENFS)             += xenfs/
+obj-$(CONFIG_XEN_SYS_HYPERVISOR)        += sys-hypervisor.o
\ No newline at end of file
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index be437c2bc942..891d2e90753a 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -151,6 +151,12 @@ static unsigned int evtchn_from_irq(unsigned irq)
         return info_for_irq(irq)->evtchn;
 }
 
+unsigned irq_from_evtchn(unsigned int evtchn)
+{
+        return evtchn_to_irq[evtchn];
+}
+EXPORT_SYMBOL_GPL(irq_from_evtchn);
+
 static enum ipi_vector ipi_from_irq(unsigned irq)
 {
         struct irq_info *info = info_for_irq(irq);
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
new file mode 100644
index 000000000000..af031950f9b1
--- /dev/null
+++ b/drivers/xen/evtchn.c
@@ -0,0 +1,507 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+        struct mutex bind_mutex; /* serialize bind/unbind operations */
+
+        /* Notification ring, accessed via /dev/xen/evtchn. */
+#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
+#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+        evtchn_port_t *ring;
+        unsigned int ring_cons, ring_prod, ring_overflow;
+        struct mutex ring_cons_mutex; /* protect against concurrent readers */
+
+        /* Processes wait on this queue when ring is empty. */
+        wait_queue_head_t evtchn_wait;
+        struct fasync_struct *evtchn_async_queue;
+        const char *name;
+};
+
+/* Who's bound to each port? */
+static struct per_user_data *port_user[NR_EVENT_CHANNELS];
+static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+
+irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+        unsigned int port = (unsigned long)data;
+        struct per_user_data *u;
+
+        spin_lock(&port_user_lock);
+
+        u = port_user[port];
+
+        disable_irq_nosync(irq);
+
+        if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
+                u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+                wmb(); /* Ensure ring contents visible */
+                if (u->ring_cons == u->ring_prod++) {
+                        wake_up_interruptible(&u->evtchn_wait);
+                        kill_fasync(&u->evtchn_async_queue,
+                                    SIGIO, POLL_IN);
+                }
+        } else {
+                u->ring_overflow = 1;
+        }
+
+        spin_unlock(&port_user_lock);
+
+        return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+                           size_t count, loff_t *ppos)
+{
+        int rc;
+        unsigned int c, p, bytes1 = 0, bytes2 = 0;
+        struct per_user_data *u = file->private_data;
+
+        /* Whole number of ports. */
+        count &= ~(sizeof(evtchn_port_t)-1);
+
+        if (count == 0)
+                return 0;
+
+        if (count > PAGE_SIZE)
+                count = PAGE_SIZE;
+
+        for (;;) {
+                mutex_lock(&u->ring_cons_mutex);
+
+                rc = -EFBIG;
+                if (u->ring_overflow)
+                        goto unlock_out;
+
+                c = u->ring_cons;
+                p = u->ring_prod;
+                if (c != p)
+                        break;
+
+                mutex_unlock(&u->ring_cons_mutex);
+
+                if (file->f_flags & O_NONBLOCK)
+                        return -EAGAIN;
+
+                rc = wait_event_interruptible(u->evtchn_wait,
+                                              u->ring_cons != u->ring_prod);
+                if (rc)
+                        return rc;
+        }
+
+        /* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+        if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
+                bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+                        sizeof(evtchn_port_t);
+                bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+        } else {
+                bytes1 = (p - c) * sizeof(evtchn_port_t);
+                bytes2 = 0;
+        }
+
+        /* Truncate chunks according to caller's maximum byte count. */
+        if (bytes1 > count) {
+                bytes1 = count;
+                bytes2 = 0;
+        } else if ((bytes1 + bytes2) > count) {
+                bytes2 = count - bytes1;
+        }
+
+        rc = -EFAULT;
+        rmb(); /* Ensure that we see the port before we copy it. */
+        if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+            ((bytes2 != 0) &&
+             copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+                goto unlock_out;
+
+        u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
+        rc = bytes1 + bytes2;
+
+ unlock_out:
+        mutex_unlock(&u->ring_cons_mutex);
+        return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+                            size_t count, loff_t *ppos)
+{
+        int rc, i;
+        evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+        struct per_user_data *u = file->private_data;
+
+        if (kbuf == NULL)
+                return -ENOMEM;
+
+        /* Whole number of ports. */
+        count &= ~(sizeof(evtchn_port_t)-1);
+
+        rc = 0;
+        if (count == 0)
+                goto out;
+
+        if (count > PAGE_SIZE)
+                count = PAGE_SIZE;
+
+        rc = -EFAULT;
+        if (copy_from_user(kbuf, buf, count) != 0)
+                goto out;
+
+        spin_lock_irq(&port_user_lock);
+        for (i = 0; i < (count/sizeof(evtchn_port_t)); i++)
+                if ((kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u))
+                        enable_irq(irq_from_evtchn(kbuf[i]));
+        spin_unlock_irq(&port_user_lock);
+
+        rc = count;
+
+ out:
+        free_page((unsigned long)kbuf);
+        return rc;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, int port)
+{
+        int rc = 0;
+
+        /*
+         * Ports are never reused, so every caller should pass in a
+         * unique port.
+         *
+         * (Locking not necessary because we haven't registered the
+         * interrupt handler yet, and our caller has already
+         * serialized bind operations.)
+         */
+        BUG_ON(port_user[port] != NULL);
+        port_user[port] = u;
+
+        rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+                                       u->name, (void *)(unsigned long)port);
+        if (rc >= 0)
+                rc = 0;
+
+        return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+{
+        int irq = irq_from_evtchn(port);
+
+        unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+
+        /* make sure we unbind the irq handler before clearing the port */
+        barrier();
+
+        port_user[port] = NULL;
+}
+
+static long evtchn_ioctl(struct file *file,
+                         unsigned int cmd, unsigned long arg)
+{
+        int rc;
+        struct per_user_data *u = file->private_data;
+        void __user *uarg = (void __user *) arg;
+
+        /* Prevent bind from racing with unbind */
+        mutex_lock(&u->bind_mutex);
+
+        switch (cmd) {
+        case IOCTL_EVTCHN_BIND_VIRQ: {
+                struct ioctl_evtchn_bind_virq bind;
+                struct evtchn_bind_virq bind_virq;
+
+                rc = -EFAULT;
+                if (copy_from_user(&bind, uarg, sizeof(bind)))
+                        break;
+
+                bind_virq.virq = bind.virq;
+                bind_virq.vcpu = 0;
+                rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+                                                 &bind_virq);
+                if (rc != 0)
+                        break;
+
+                rc = evtchn_bind_to_user(u, bind_virq.port);
+                if (rc == 0)
+                        rc = bind_virq.port;
+                break;
+        }
+
+        case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+                struct ioctl_evtchn_bind_interdomain bind;
+                struct evtchn_bind_interdomain bind_interdomain;
+
+                rc = -EFAULT;
+                if (copy_from_user(&bind, uarg, sizeof(bind)))
+                        break;
+
+                bind_interdomain.remote_dom  = bind.remote_domain;
+                bind_interdomain.remote_port = bind.remote_port;
+                rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+                                                 &bind_interdomain);
+                if (rc != 0)
+                        break;
+
+                rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+                if (rc == 0)
+                        rc = bind_interdomain.local_port;
+                break;
+        }
+
+        case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+                struct ioctl_evtchn_bind_unbound_port bind;
+                struct evtchn_alloc_unbound alloc_unbound;
+
+                rc = -EFAULT;
+                if (copy_from_user(&bind, uarg, sizeof(bind)))
+                        break;
+
+                alloc_unbound.dom        = DOMID_SELF;
+                alloc_unbound.remote_dom = bind.remote_domain;
+                rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+                                                 &alloc_unbound);
+                if (rc != 0)
+                        break;
+
+                rc = evtchn_bind_to_user(u, alloc_unbound.port);
+                if (rc == 0)
+                        rc = alloc_unbound.port;
+                break;
+        }
+
+        case IOCTL_EVTCHN_UNBIND: {
+                struct ioctl_evtchn_unbind unbind;
+
+                rc = -EFAULT;
+                if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+                        break;
+
+                rc = -EINVAL;
+                if (unbind.port >= NR_EVENT_CHANNELS)
+                        break;
+
+                spin_lock_irq(&port_user_lock);
+
+                rc = -ENOTCONN;
+                if (port_user[unbind.port] != u) {
+                        spin_unlock_irq(&port_user_lock);
+                        break;
+                }
+
+                evtchn_unbind_from_user(u, unbind.port);
+
+                spin_unlock_irq(&port_user_lock);
+
+                rc = 0;
+                break;
+        }
+
+        case IOCTL_EVTCHN_NOTIFY: {
+                struct ioctl_evtchn_notify notify;
+
+                rc = -EFAULT;
+                if (copy_from_user(&notify, uarg, sizeof(notify)))
+                        break;
+
+                if (notify.port >= NR_EVENT_CHANNELS) {
+                        rc = -EINVAL;
+                } else if (port_user[notify.port] != u) {
+                        rc = -ENOTCONN;
+                } else {
+                        notify_remote_via_evtchn(notify.port);
+                        rc = 0;
+                }
+                break;
+        }
+
+        case IOCTL_EVTCHN_RESET: {
+                /* Initialise the ring to empty. Clear errors. */
+                mutex_lock(&u->ring_cons_mutex);
+                spin_lock_irq(&port_user_lock);
+                u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+                spin_unlock_irq(&port_user_lock);
+                mutex_unlock(&u->ring_cons_mutex);
+                rc = 0;
+                break;
+        }
+
+        default:
+                rc = -ENOSYS;
+                break;
+        }
+        mutex_unlock(&u->bind_mutex);
+
+        return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+        unsigned int mask = POLLOUT | POLLWRNORM;
+        struct per_user_data *u = file->private_data;
+
+        poll_wait(file, &u->evtchn_wait, wait);
+        if (u->ring_cons != u->ring_prod)
+                mask |= POLLIN | POLLRDNORM;
+        if (u->ring_overflow)
+                mask = POLLERR;
+        return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+        struct per_user_data *u = filp->private_data;
+        return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+        struct per_user_data *u;
+
+        u = kzalloc(sizeof(*u), GFP_KERNEL);
+        if (u == NULL)
+                return -ENOMEM;
+
+        u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+        if (u->name == NULL) {
+                kfree(u);
+                return -ENOMEM;
+        }
+
+        init_waitqueue_head(&u->evtchn_wait);
+
+        u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+        if (u->ring == NULL) {
+                kfree(u->name);
+                kfree(u);
+                return -ENOMEM;
+        }
+
+        mutex_init(&u->bind_mutex);
+        mutex_init(&u->ring_cons_mutex);
+
+        filp->private_data = u;
+
+        return 0;
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+        int i;
+        struct per_user_data *u = filp->private_data;
+
+        spin_lock_irq(&port_user_lock);
+
+        free_page((unsigned long)u->ring);
+
+        for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+                if (port_user[i] != u)
+                        continue;
+
+                evtchn_unbind_from_user(port_user[i], i);
+        }
+
+        spin_unlock_irq(&port_user_lock);
+
+        kfree(u->name);
+        kfree(u);
+
+        return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+        .owner   = THIS_MODULE,
+        .read    = evtchn_read,
+        .write   = evtchn_write,
+        .unlocked_ioctl = evtchn_ioctl,
+        .poll    = evtchn_poll,
+        .fasync  = evtchn_fasync,
+        .open    = evtchn_open,
+        .release = evtchn_release,
+};
+
+static struct miscdevice evtchn_miscdev = {
+        .minor        = MISC_DYNAMIC_MINOR,
+        .name         = "evtchn",
+        .fops         = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+        int err;
+
+        if (!xen_domain())
+                return -ENODEV;
+
+        spin_lock_init(&port_user_lock);
+        memset(port_user, 0, sizeof(port_user));
+
+        /* Create '/dev/misc/evtchn'. */
+        err = misc_register(&evtchn_miscdev);
+        if (err != 0) {
+                printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+                return err;
+        }
+
+        printk(KERN_INFO "Event-channel device installed.\n");
+
+        return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+        misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 4b5b84837ee1..fddc2025dece 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -98,9 +98,8 @@ static void do_suspend(void)
                 goto out;
         }
 
-        printk("suspending xenbus...\n");
-        /* XXX use normal device tree? */
-        xenbus_suspend();
+        printk(KERN_DEBUG "suspending xenstore...\n");
+        xs_suspend();
 
         err = device_power_down(PMSG_SUSPEND);
         if (err) {
@@ -116,9 +115,9 @@ static void do_suspend(void)
 
         if (!cancelled) {
                 xen_arch_resume();
-                xenbus_resume();
+                xs_resume();
         } else
-                xenbus_suspend_cancel();
+                xs_suspend_cancel();
 
         device_power_up(PMSG_RESUME);
 
diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
new file mode 100644
index 000000000000..88a60e03ccf0
--- /dev/null
+++ b/drivers/xen/sys-hypervisor.c
@@ -0,0 +1,445 @@
+/*
+ *  copyright (c) 2006 IBM Corporation
+ *  Authored by: Mike D. Day <ncmike@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr  _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = \
+        __ATTR(_name, 0644, _name##_show, _name##_store)
+
+struct hyp_sysfs_attr {
+        struct attribute attr;
+        ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+        ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+        void *hyp_attr_data;
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+        return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static void xen_sysfs_type_destroy(void)
+{
+        sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+        if (version)
+                return sprintf(buffer, "%d\n", version >> 16);
+        return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+        if (version)
+                return sprintf(buffer, "%d\n", version & 0xff);
+        return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        char *extra;
+
+        extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+        if (extra) {
+                ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", extra);
+                kfree(extra);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+        &major_attr.attr,
+        &minor_attr.attr,
+        &extra_attr.attr,
+        NULL
+};
+
+static struct attribute_group version_group = {
+        .name = "version",
+        .attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+        return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+static void xen_sysfs_version_destroy(void)
+{
+        sysfs_remove_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        char *vm, *val;
+        int ret;
+        extern int xenstored_ready;
+
+        if (!xenstored_ready)
+                return -EBUSY;
+
+        vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+        if (IS_ERR(vm))
+                return PTR_ERR(vm);
+        val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+        kfree(vm);
+        if (IS_ERR(val))
+                return PTR_ERR(val);
+        ret = sprintf(buffer, "%s\n", val);
+        kfree(val);
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+        return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+static void xen_sysfs_uuid_destroy(void)
+{
+        sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        struct xen_compile_info *info;
+
+        info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+        if (info) {
+                ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", info->compiler);
+                kfree(info);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        struct xen_compile_info *info;
+
+        info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+        if (info) {
+                ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", info->compile_by);
+                kfree(info);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        struct xen_compile_info *info;
+
+        info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+        if (info) {
+                ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", info->compile_date);
+                kfree(info);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+        &compiler_attr.attr,
+        &compiled_by_attr.attr,
+        &compile_date_attr.attr,
+        NULL
+};
+
+static struct attribute_group xen_compilation_group = {
+        .name = "compilation",
+        .attrs = xen_compile_attrs,
+};
+
+int __init static xen_compilation_init(void)
+{
+        return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+static void xen_compilation_destroy(void)
+{
+        sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        char *caps;
+
+        caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+        if (caps) {
+                ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", caps);
+                kfree(caps);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        char *cset;
+
+        cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+        if (cset) {
+                ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+                if (!ret)
+                        ret = sprintf(buffer, "%s\n", cset);
+                kfree(cset);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret = -ENOMEM;
+        struct xen_platform_parameters *parms;
+
+        parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+        if (parms) {
+                ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+                                             parms);
+                if (!ret)
+                        ret = sprintf(buffer, "%lx\n", parms->virt_start);
+                kfree(parms);
+        }
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        int ret;
+
+        ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+        if (ret > 0)
+                ret = sprintf(buffer, "%x\n", ret);
+
+        return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+        ssize_t ret;
+        struct xen_feature_info info;
+
+        info.submap_idx = index;
+        ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+        if (!ret)
+                ret = sprintf(buffer, "%08x", info.submap);
+
+        return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+        ssize_t len;
+        int i;
+
+        len = 0;
+        for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+                int ret = xen_feature_show(i, buffer + len);
+                if (ret < 0) {
+                        if (len == 0)
+                                len = ret;
+                        break;
+                }
+                len += ret;
+        }
+        if (len > 0)
+                buffer[len++] = '\n';
+
+        return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static struct attribute *xen_properties_attrs[] = {
+        &capabilities_attr.attr,
+        &changeset_attr.attr,
+        &virtual_start_attr.attr,
+        &pagesize_attr.attr,
+        &features_attr.attr,
+        NULL
+};
+
+static struct attribute_group xen_properties_group = {
+        .name = "properties",
+        .attrs = xen_properties_attrs,
+};
+
+static int __init xen_properties_init(void)
+{
+        return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static void xen_properties_destroy(void)
+{
+        sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static int __init hyper_sysfs_init(void)
+{
+        int ret;
+
+        if (!xen_domain())
+                return -ENODEV;
+
+        ret = xen_sysfs_type_init();
+        if (ret)
+                goto out;
+        ret = xen_sysfs_version_init();
+        if (ret)
+                goto version_out;
+        ret = xen_compilation_init();
+        if (ret)
+                goto comp_out;
+        ret = xen_sysfs_uuid_init();
+        if (ret)
+                goto uuid_out;
+        ret = xen_properties_init();
+        if (ret)
+                goto prop_out;
+
+        goto out;
+
+prop_out:
+        xen_sysfs_uuid_destroy();
+uuid_out:
+        xen_compilation_destroy();
+comp_out:
+        xen_sysfs_version_destroy();
+version_out:
+        xen_sysfs_type_destroy();
+out:
+        return ret;
+}
+
+static void __exit hyper_sysfs_exit(void)
+{
+        xen_properties_destroy();
+        xen_compilation_destroy();
+        xen_sysfs_uuid_destroy();
+        xen_sysfs_version_destroy();
+        xen_sysfs_type_destroy();
+
+}
+module_init(hyper_sysfs_init);
+module_exit(hyper_sysfs_exit);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+                              struct attribute *attr,
+                              char *buffer)
+{
+        struct hyp_sysfs_attr *hyp_attr;
+        hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+        if (hyp_attr->show)
+                return hyp_attr->show(hyp_attr, buffer);
+        return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+                               struct attribute *attr,
+                               const char *buffer,
+                               size_t len)
+{
+        struct hyp_sysfs_attr *hyp_attr;
+        hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+        if (hyp_attr->store)
+                return hyp_attr->store(hyp_attr, buffer, len);
+        return 0;
+}
+
+static struct sysfs_ops hyp_sysfs_ops = {
+        .show = hyp_sysfs_show,
+        .store = hyp_sysfs_store,
+};
+
+static struct kobj_type hyp_sysfs_kobj_type = {
+        .sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+        if (!xen_domain())
+                return -ENODEV;
+
+        hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+        return 0;
+}
+device_initcall(hypervisor_subsys_init);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 773d1cf23283..d42e25d5968d 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -71,6 +71,9 @@ static int xenbus_probe_frontend(const char *type, const char *name);
 
 static void xenbus_dev_shutdown(struct device *_dev);
 
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state);
+static int xenbus_dev_resume(struct device *dev);
+
 /* If something in array of ids matches this device, return it. */
 static const struct xenbus_device_id *
 match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
@@ -188,6 +191,9 @@ static struct xen_bus_type xenbus_frontend = {
                 .remove    = xenbus_dev_remove,
                 .shutdown  = xenbus_dev_shutdown,
                 .dev_attrs = xenbus_dev_attrs,
+
+                .suspend   = xenbus_dev_suspend,
+                .resume    = xenbus_dev_resume,
         },
 };
 
@@ -654,6 +660,7 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 
         kfree(root);
 }
+EXPORT_SYMBOL_GPL(xenbus_dev_changed);
 
 static void frontend_changed(struct xenbus_watch *watch,
                              const char **vec, unsigned int len)
@@ -669,7 +676,7 @@ static struct xenbus_watch fe_watch = {
         .callback = frontend_changed,
 };
 
-static int suspend_dev(struct device *dev, void *data)
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state)
 {
         int err = 0;
         struct xenbus_driver *drv;
@@ -682,35 +689,14 @@ static int suspend_dev(struct device *dev, void *data)
         drv = to_xenbus_driver(dev->driver);
         xdev = container_of(dev, struct xenbus_device, dev);
         if (drv->suspend)
-                err = drv->suspend(xdev);
+                err = drv->suspend(xdev, state);
         if (err)
                 printk(KERN_WARNING
                        "xenbus: suspend %s failed: %i\n", dev_name(dev), err);
         return 0;
 }
 
-static int suspend_cancel_dev(struct device *dev, void *data)
-{
-        int err = 0;
-        struct xenbus_driver *drv;
-        struct xenbus_device *xdev;
-
-        DPRINTK("");
-
-        if (dev->driver == NULL)
-                return 0;
-        drv = to_xenbus_driver(dev->driver);
-        xdev = container_of(dev, struct xenbus_device, dev);
-        if (drv->suspend_cancel)
-                err = drv->suspend_cancel(xdev);
-        if (err)
-                printk(KERN_WARNING
-                       "xenbus: suspend_cancel %s failed: %i\n",
-                       dev_name(dev), err);
-        return 0;
-}
-
-static int resume_dev(struct device *dev, void *data)
+static int xenbus_dev_resume(struct device *dev)
 {
         int err;
         struct xenbus_driver *drv;
@@ -755,33 +741,6 @@ static int resume_dev(struct device *dev, void *data)
         return 0;
 }
 
-void xenbus_suspend(void)
-{
-        DPRINTK("");
-
-        bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_dev);
-        xenbus_backend_suspend(suspend_dev);
-        xs_suspend();
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend);
-
-void xenbus_resume(void)
-{
-        xb_init_comms();
-        xs_resume();
-        bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, resume_dev);
-        xenbus_backend_resume(resume_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_resume);
-
-void xenbus_suspend_cancel(void)
-{
-        xs_suspend_cancel();
-        bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_cancel_dev);
-        xenbus_backend_resume(suspend_cancel_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend_cancel);
-
 /* A flag to determine if xenstored is 'ready' (i.e. has started) */
 int xenstored_ready = 0;
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index e325eab4724d..eab33f1dbdf7 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -673,6 +673,8 @@ void xs_resume(void)
         struct xenbus_watch *watch;
         char token[sizeof(watch) * 2 + 1];
 
+        xb_init_comms();
+
         mutex_unlock(&xs_state.response_mutex);
         mutex_unlock(&xs_state.request_mutex);
         up_write(&xs_state.transaction_mutex);
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 515741a8e6b8..6559e0c752ce 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -20,10 +20,27 @@
 MODULE_DESCRIPTION("Xen filesystem");
 MODULE_LICENSE("GPL");
 
+static ssize_t capabilities_read(struct file *file, char __user *buf,
+                                 size_t size, loff_t *off)
+{
+        char *tmp = "";
+
+        if (xen_initial_domain())
+                tmp = "control_d\n";
+
+        return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
+}
+
+static const struct file_operations capabilities_file_ops = {
+        .read = capabilities_read,
+};
+
 static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
 {
         static struct tree_descr xenfs_files[] = {
-                [2] = {"xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR},
+                [1] = {},
+                { "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
+                { "capabilities", &capabilities_file_ops, S_IRUGO },
                 {""},
         };
 
diff --git a/include/Kbuild b/include/Kbuild
index d8c3e3cbf416..fe36accd4328 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -8,3 +8,4 @@ header-y += mtd/
 header-y += rdma/
 header-y += video/
 header-y += drm/
+header-y += xen/
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e6d0ca70aba..e410f602cab1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -280,17 +280,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif
 
 /*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests.  By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
  */
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode()      do {} while (0)
-#define arch_leave_lazy_cpu_mode()      do {} while (0)
-#define arch_flush_lazy_cpu_mode()      do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev) do {} while (0)
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING
diff --git a/include/xen/Kbuild b/include/xen/Kbuild
new file mode 100644
index 000000000000..4e65c16a445b
--- /dev/null
+++ b/include/xen/Kbuild
@@ -0,0 +1 @@
+header-y += evtchn.h
diff --git a/include/xen/events.h b/include/xen/events.h
index 0d5f1adc0363..e68d59a90ca8 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -53,4 +53,7 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
 #endif  /* _XEN_EVENTS_H */
diff --git a/include/xen/evtchn.h b/include/xen/evtchn.h
new file mode 100644
index 000000000000..14e833ee4e0b
--- /dev/null
+++ b/include/xen/evtchn.h
@@ -0,0 +1,88 @@
+/******************************************************************************
+ * evtchn.h
+ *
+ * Interface to /dev/xen/evtchn.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_EVTCHN_H__
+#define __LINUX_PUBLIC_EVTCHN_H__
+
+/*
+ * Bind a fresh port to VIRQ @virq.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_VIRQ                          \
+        _IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq))
+struct ioctl_evtchn_bind_virq {
+        unsigned int virq;
+};
+
+/*
+ * Bind a fresh port to remote <@remote_domain, @remote_port>.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_INTERDOMAIN                   \
+        _IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain))
+struct ioctl_evtchn_bind_interdomain {
+        unsigned int remote_domain, remote_port;
+};
+
+/*
+ * Allocate a fresh port for binding to @remote_domain.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_UNBOUND_PORT                  \
+        _IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port))
+struct ioctl_evtchn_bind_unbound_port {
+        unsigned int remote_domain;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_UNBIND                             \
+        _IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind))
+struct ioctl_evtchn_unbind {
+        unsigned int port;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_NOTIFY                             \
+        _IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify))
+struct ioctl_evtchn_notify {
+        unsigned int port;
+};
+
+/* Clear and reinitialise the event buffer. Clear error condition. */
+#define IOCTL_EVTCHN_RESET                              \
+        _IOC(_IOC_NONE, 'E', 5, 0)
+
+#endif /* __LINUX_PUBLIC_EVTCHN_H__ */
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 453235e923f0..e8b6519d47e9 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -57,4 +57,7 @@ struct xen_feature_info {
 /* Declares the features reported by XENVER_get_features. */
 #include "features.h"
 
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
 #endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index f87f9614844d..b9763badbd77 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -91,8 +91,7 @@ struct xenbus_driver {
         void (*otherend_changed)(struct xenbus_device *dev,
                                  enum xenbus_state backend_state);
         int (*remove)(struct xenbus_device *dev);
-        int (*suspend)(struct xenbus_device *dev);
-        int (*suspend_cancel)(struct xenbus_device *dev);
+        int (*suspend)(struct xenbus_device *dev, pm_message_t state);
         int (*resume)(struct xenbus_device *dev);
         int (*uevent)(struct xenbus_device *, char **, int, char *, int);
         struct device_driver driver;
diff --git a/kernel/sched.c b/kernel/sched.c
index c3c04e256560..076e403b9c88 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2783,7 +2783,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
          * combine the page table reload and the switch backend into
          * one hypercall.
          */
-        arch_enter_lazy_cpu_mode();
+        arch_start_context_switch(prev);
 
         if (unlikely(!mm)) {
                 next->active_mm = oldmm;