Pull pvops into release branch

16 files changed, 960 insertions, 303 deletions

diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index e67ee3f27698..905d25b13d5a 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -100,3 +100,9 @@ define archhelp
   echo '  boot          - Build vmlinux and bootloader for Ski simulator'
   echo '* unwcheck      - Check vmlinux for invalid unwind info'
 endef
+
+archprepare: make_nr_irqs_h FORCE
+PHONY += make_nr_irqs_h FORCE
+
+make_nr_irqs_h: FORCE
+        $(Q)$(MAKE) $(build)=arch/ia64/kernel include/asm-ia64/nr-irqs.h
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 13fd10e8699e..87fea11aecb7 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -36,6 +36,8 @@ obj-$(CONFIG_PCI_MSI)		+= msi_ia64.o
 mca_recovery-y                  += mca_drv.o mca_drv_asm.o
 obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
 
+obj-$(CONFIG_PARAVIRT)          += paravirt.o paravirtentry.o
+
 obj-$(CONFIG_IA64_ESI)          += esi.o
 ifneq ($(CONFIG_IA64_ESI),)
 obj-y                           += esi_stub.o   # must be in kernel proper
@@ -70,3 +72,45 @@ $(obj)/gate-syms.o: $(obj)/gate.lds $(obj)/gate.o FORCE
 # We must build gate.so before we can assemble it.
 # Note: kbuild does not track this dependency due to usage of .incbin
 $(obj)/gate-data.o: $(obj)/gate.so
+
+# Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
+define sed-y
+        "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
+endef
+quiet_cmd_nr_irqs = GEN     $@
+define cmd_nr_irqs
+        (set -e; \
+         echo "#ifndef __ASM_NR_IRQS_H__"; \
+         echo "#define __ASM_NR_IRQS_H__"; \
+         echo "/*"; \
+         echo " * DO NOT MODIFY."; \
+         echo " *"; \
+         echo " * This file was generated by Kbuild"; \
+         echo " *"; \
+         echo " */"; \
+         echo ""; \
+         sed -ne $(sed-y) $<; \
+         echo ""; \
+         echo "#endif" ) > $@
+endef
+
+# We use internal kbuild rules to avoid the "is up to date" message from make
+arch/$(SRCARCH)/kernel/nr-irqs.s: $(srctree)/arch/$(SRCARCH)/kernel/nr-irqs.c \
+                                $(wildcard $(srctree)/include/asm-ia64/*/irq.h)
+        $(Q)mkdir -p $(dir $@)
+        $(call if_changed_dep,cc_s_c)
+
+include/asm-ia64/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
+        $(Q)mkdir -p $(dir $@)
+        $(call cmd,nr_irqs)
+
+clean-files += $(objtree)/include/asm-ia64/nr-irqs.h
+
+#
+# native ivt.S and entry.S
+#
+ASM_PARAVIRT_OBJS = ivt.o entry.o
+define paravirtualized_native
+AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
+endef
+$(foreach obj,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_native,$(obj))))
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index ca2bb95726de..56ab156c48ae 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -23,6 +23,11 @@
  * 11/07/2000
  */
 /*
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *                    pv_ops.
+ */
+/*
  * Global (preserved) predicate usage on syscall entry/exit path:
  *
  *      pKStk:          See entry.h.
@@ -45,6 +50,7 @@
 
 #include "minstate.h"
 
+#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
         /*
          * execve() is special because in case of success, we need to
          * setup a null register window frame.
@@ -173,6 +179,7 @@ GLOBAL_ENTRY(sys_clone)
         mov rp=loc0
         br.ret.sptk.many rp
 END(sys_clone)
+#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 /*
  * prev_task <- ia64_switch_to(struct task_struct *next)
@@ -180,7 +187,7 @@ END(sys_clone)
  *      called.  The code starting at .map relies on this.  The rest of the code
  *      doesn't care about the interrupt masking status.
  */
-GLOBAL_ENTRY(ia64_switch_to)
+GLOBAL_ENTRY(__paravirt_switch_to)
         .prologue
         alloc r16=ar.pfs,1,0,0,0
         DO_SAVE_SWITCH_STACK
@@ -204,7 +211,7 @@ GLOBAL_ENTRY(ia64_switch_to)
         ;;
 .done:
         ld8 sp=[r21]                    // load kernel stack pointer of new task
-        mov IA64_KR(CURRENT)=in0        // update "current" application register
+        MOV_TO_KR(CURRENT, in0, r8, r9)         // update "current" application register
         mov r8=r13                      // return pointer to previously running task
         mov r13=in0                     // set "current" pointer
         ;;
@@ -216,26 +223,25 @@ GLOBAL_ENTRY(ia64_switch_to)
         br.ret.sptk.many rp             // boogie on out in new context
 
 .map:
-        rsm psr.ic                      // interrupts (psr.i) are already disabled here
+        RSM_PSR_IC(r25)                 // interrupts (psr.i) are already disabled here
         movl r25=PAGE_KERNEL
         ;;
         srlz.d
         or r23=r25,r20                  // construct PA | page properties
         mov r25=IA64_GRANULE_SHIFT<<2
         ;;
-        mov cr.itir=r25
-        mov cr.ifa=in0                  // VA of next task...
+        MOV_TO_ITIR(p0, r25, r8)
+        MOV_TO_IFA(in0, r8)             // VA of next task...
         ;;
         mov r25=IA64_TR_CURRENT_STACK
-        mov IA64_KR(CURRENT_STACK)=r26  // remember last page we mapped...
+        MOV_TO_KR(CURRENT_STACK, r26, r8, r9)   // remember last page we mapped...
         ;;
         itr.d dtr[r25]=r23              // wire in new mapping...
-        ssm psr.ic                      // reenable the psr.ic bit
-        ;;
-        srlz.d
+        SSM_PSR_IC_AND_SRLZ_D(r8, r9)   // reenable the psr.ic bit
         br.cond.sptk .done
-END(ia64_switch_to)
+END(__paravirt_switch_to)
 
+#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 /*
  * Note that interrupts are enabled during save_switch_stack and load_switch_stack.  This
  * means that we may get an interrupt with "sp" pointing to the new kernel stack while
@@ -375,7 +381,7 @@ END(save_switch_stack)
  *      - b7 holds address to return to
  *      - must not touch r8-r11
  */
-ENTRY(load_switch_stack)
+GLOBAL_ENTRY(load_switch_stack)
         .prologue
         .altrp b7
 
@@ -571,7 +577,7 @@ GLOBAL_ENTRY(ia64_trace_syscall)
 .ret3:
 (pUStk) cmp.eq.unc p6,p0=r0,r0                  // p6 <- pUStk
 (pUStk) rsm psr.i                               // disable interrupts
-        br.cond.sptk .work_pending_syscall_end
+        br.cond.sptk ia64_work_pending_syscall_end
 
 strace_error:
         ld8 r3=[r2]                             // load pt_regs.r8
@@ -636,8 +642,17 @@ GLOBAL_ENTRY(ia64_ret_from_syscall)
         adds r2=PT(R8)+16,sp                    // r2 = &pt_regs.r8
         mov r10=r0                              // clear error indication in r10
 (p7)    br.cond.spnt handle_syscall_error       // handle potential syscall failure
+#ifdef CONFIG_PARAVIRT
+        ;;
+        br.cond.sptk.few ia64_leave_syscall
+        ;;
+#endif /* CONFIG_PARAVIRT */
 END(ia64_ret_from_syscall)
+#ifndef CONFIG_PARAVIRT
         // fall through
+#endif
+#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
+
 /*
  * ia64_leave_syscall(): Same as ia64_leave_kernel, except that it doesn't
  *      need to switch to bank 0 and doesn't restore the scratch registers.
@@ -682,7 +697,7 @@ END(ia64_ret_from_syscall)
  *            ar.csd: cleared
  *            ar.ssd: cleared
  */
-ENTRY(ia64_leave_syscall)
+GLOBAL_ENTRY(__paravirt_leave_syscall)
         PT_REGS_UNWIND_INFO(0)
         /*
          * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -692,11 +707,11 @@ ENTRY(ia64_leave_syscall)
          * extra work.  We always check for extra work when returning to user-level.
          * With CONFIG_PREEMPT, we also check for extra work when the preempt_count
          * is 0.  After extra work processing has been completed, execution
-         * resumes at .work_processed_syscall with p6 set to 1 if the extra-work-check
+         * resumes at ia64_work_processed_syscall with p6 set to 1 if the extra-work-check
          * needs to be redone.
          */
 #ifdef CONFIG_PREEMPT
-        rsm psr.i                               // disable interrupts
+        RSM_PSR_I(p0, r2, r18)                  // disable interrupts
         cmp.eq pLvSys,p0=r0,r0                  // pLvSys=1: leave from syscall
 (pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
         ;;
@@ -706,11 +721,12 @@ ENTRY(ia64_leave_syscall)
         ;;
         cmp.eq p6,p0=r21,r0             // p6 <- pUStk || (preempt_count == 0)
 #else /* !CONFIG_PREEMPT */
-(pUStk) rsm psr.i
+        RSM_PSR_I(pUStk, r2, r18)
         cmp.eq pLvSys,p0=r0,r0          // pLvSys=1: leave from syscall
 (pUStk) cmp.eq.unc p6,p0=r0,r0          // p6 <- pUStk
 #endif
-.work_processed_syscall:
+.global __paravirt_work_processed_syscall;
+__paravirt_work_processed_syscall:
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
         adds r2=PT(LOADRS)+16,r12
 (pUStk) mov.m r22=ar.itc                        // fetch time at leave
@@ -744,7 +760,7 @@ ENTRY(ia64_leave_syscall)
 (pNonSys) break 0               //      bug check: we shouldn't be here if pNonSys is TRUE!
         ;;
         invala                  // M0|1 invalidate ALAT
-        rsm psr.i | psr.ic      // M2   turn off interrupts and interruption collection
+        RSM_PSR_I_IC(r28, r29, r30)     // M2   turn off interrupts and interruption collection
         cmp.eq p9,p0=r0,r0      // A    set p9 to indicate that we should restore cr.ifs
 
         ld8 r29=[r2],16         // M0|1 load cr.ipsr
@@ -765,7 +781,7 @@ ENTRY(ia64_leave_syscall)
         ;;
 #endif
         ld8 r26=[r2],PT(B0)-PT(AR_PFS)  // M0|1 load ar.pfs
-(pKStk) mov r22=psr                     // M2   read PSR now that interrupts are disabled
+        MOV_FROM_PSR(pKStk, r22, r21)   // M2   read PSR now that interrupts are disabled
         nop 0
         ;;
         ld8 r21=[r2],PT(AR_RNAT)-PT(B0) // M0|1 load b0
@@ -798,7 +814,7 @@ ENTRY(ia64_leave_syscall)
 
         srlz.d                          // M0   ensure interruption collection is off (for cover)
         shr.u r18=r19,16                // I0|1 get byte size of existing "dirty" partition
-        cover                           // B    add current frame into dirty partition & set cr.ifs
+        COVER                           // B    add current frame into dirty partition & set cr.ifs
         ;;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
         mov r19=ar.bsp                  // M2   get new backing store pointer
@@ -823,8 +839,9 @@ ENTRY(ia64_leave_syscall)
         mov.m ar.ssd=r0                 // M2   clear ar.ssd
         mov f11=f0                      // F    clear f11
         br.cond.sptk.many rbs_switch    // B
-END(ia64_leave_syscall)
+END(__paravirt_leave_syscall)
 
+#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 #ifdef CONFIG_IA32_SUPPORT
 GLOBAL_ENTRY(ia64_ret_from_ia32_execve)
         PT_REGS_UNWIND_INFO(0)
@@ -835,10 +852,20 @@ GLOBAL_ENTRY(ia64_ret_from_ia32_execve)
         st8.spill [r2]=r8       // store return value in slot for r8 and set unat bit
         .mem.offset 8,0
         st8.spill [r3]=r0       // clear error indication in slot for r10 and set unat bit
+#ifdef CONFIG_PARAVIRT
+        ;;
+        // don't fall through, ia64_leave_kernel may be #define'd
+        br.cond.sptk.few ia64_leave_kernel
+        ;;
+#endif /* CONFIG_PARAVIRT */
 END(ia64_ret_from_ia32_execve)
+#ifndef CONFIG_PARAVIRT
         // fall through
+#endif
 #endif /* CONFIG_IA32_SUPPORT */
-GLOBAL_ENTRY(ia64_leave_kernel)
+#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
+
+GLOBAL_ENTRY(__paravirt_leave_kernel)
         PT_REGS_UNWIND_INFO(0)
         /*
          * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -852,7 +879,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
          * needs to be redone.
          */
 #ifdef CONFIG_PREEMPT
-        rsm psr.i                               // disable interrupts
+        RSM_PSR_I(p0, r17, r31)                 // disable interrupts
         cmp.eq p0,pLvSys=r0,r0                  // pLvSys=0: leave from kernel
 (pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
         ;;
@@ -862,7 +889,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
         ;;
         cmp.eq p6,p0=r21,r0             // p6 <- pUStk || (preempt_count == 0)
 #else
-(pUStk) rsm psr.i
+        RSM_PSR_I(pUStk, r17, r31)
         cmp.eq p0,pLvSys=r0,r0          // pLvSys=0: leave from kernel
 (pUStk) cmp.eq.unc p6,p0=r0,r0          // p6 <- pUStk
 #endif
@@ -910,7 +937,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
         mov ar.csd=r30
         mov ar.ssd=r31
         ;;
-        rsm psr.i | psr.ic      // initiate turning off of interrupt and interruption collection
+        RSM_PSR_I_IC(r23, r22, r25)     // initiate turning off of interrupt and interruption collection
         invala                  // invalidate ALAT
         ;;
         ld8.fill r22=[r2],24
@@ -942,7 +969,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
         mov ar.ccv=r15
         ;;
         ldf.fill f11=[r2]
-        bsw.0                   // switch back to bank 0 (no stop bit required beforehand...)
+        BSW_0(r2, r3, r15)      // switch back to bank 0 (no stop bit required beforehand...)
         ;;
 (pUStk) mov r18=IA64_KR(CURRENT)// M2 (12 cycle read latency)
         adds r16=PT(CR_IPSR)+16,r12
@@ -950,12 +977,12 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
         .pred.rel.mutex pUStk,pKStk
-(pKStk) mov r22=psr             // M2 read PSR now that interrupts are disabled
+        MOV_FROM_PSR(pKStk, r22, r29)   // M2 read PSR now that interrupts are disabled
 (pUStk) mov.m r22=ar.itc        // M  fetch time at leave
         nop.i 0
         ;;
 #else
-(pKStk) mov r22=psr             // M2 read PSR now that interrupts are disabled
+        MOV_FROM_PSR(pKStk, r22, r29)   // M2 read PSR now that interrupts are disabled
         nop.i 0
         nop.i 0
         ;;
@@ -1027,7 +1054,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
          * NOTE: alloc, loadrs, and cover can't be predicated.
          */
 (pNonSys) br.cond.dpnt dont_preserve_current_frame
-        cover                           // add current frame into dirty partition and set cr.ifs
+        COVER                           // add current frame into dirty partition and set cr.ifs
         ;;
         mov r19=ar.bsp                  // get new backing store pointer
 rbs_switch:
@@ -1130,16 +1157,16 @@ skip_rbs_switch:
 (pKStk) dep r29=r22,r29,21,1    // I0 update ipsr.pp with psr.pp
 (pLvSys)mov r16=r0              // A  clear r16 for leave_syscall, no-op otherwise
         ;;
-        mov cr.ipsr=r29         // M2
+        MOV_TO_IPSR(p0, r29, r25)       // M2
         mov ar.pfs=r26          // I0
 (pLvSys)mov r17=r0              // A  clear r17 for leave_syscall, no-op otherwise
 
-(p9)    mov cr.ifs=r30          // M2
+        MOV_TO_IFS(p9, r30, r25)// M2
         mov b0=r21              // I0
 (pLvSys)mov r18=r0              // A  clear r18 for leave_syscall, no-op otherwise
 
         mov ar.fpsr=r20         // M2
-        mov cr.iip=r28          // M2
+        MOV_TO_IIP(r28, r25)    // M2
         nop 0
         ;;
 (pUStk) mov ar.rnat=r24         // M2 must happen with RSE in lazy mode
@@ -1148,7 +1175,7 @@ skip_rbs_switch:
 
         mov ar.rsc=r27          // M2
         mov pr=r31,-1           // I0
-        rfi                     // B
+        RFI                     // B
 
         /*
          * On entry:
@@ -1174,35 +1201,36 @@ skip_rbs_switch:
         ;;
 (pKStk) st4 [r20]=r21
 #endif
-        ssm psr.i               // enable interrupts
+        SSM_PSR_I(p0, p6, r2)   // enable interrupts
         br.call.spnt.many rp=schedule
 .ret9:  cmp.eq p6,p0=r0,r0      // p6 <- 1 (re-check)
-        rsm psr.i               // disable interrupts
+        RSM_PSR_I(p0, r2, r20)  // disable interrupts
         ;;
 #ifdef CONFIG_PREEMPT
 (pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
         ;;
 (pKStk) st4 [r20]=r0            // preempt_count() <- 0
 #endif
-(pLvSys)br.cond.sptk.few  .work_pending_syscall_end
+(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
         br.cond.sptk.many .work_processed_kernel
 
 .notify:
 (pUStk) br.call.spnt.many rp=notify_resume_user
 .ret10: cmp.ne p6,p0=r0,r0      // p6 <- 0 (don't re-check)
-(pLvSys)br.cond.sptk.few  .work_pending_syscall_end
+(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
         br.cond.sptk.many .work_processed_kernel
 
-.work_pending_syscall_end:
+.global __paravirt_pending_syscall_end;
+__paravirt_pending_syscall_end:
         adds r2=PT(R8)+16,r12
         adds r3=PT(R10)+16,r12
         ;;
         ld8 r8=[r2]
         ld8 r10=[r3]
-        br.cond.sptk.many .work_processed_syscall
-
-END(ia64_leave_kernel)
+        br.cond.sptk.many __paravirt_work_processed_syscall_target
+END(__paravirt_leave_kernel)
 
+#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 ENTRY(handle_syscall_error)
         /*
          * Some system calls (e.g., ptrace, mmap) can return arbitrary values which could
@@ -1244,7 +1272,7 @@ END(ia64_invoke_schedule_tail)
          * We declare 8 input registers so the system call args get preserved,
          * in case we need to restart a system call.
          */
-ENTRY(notify_resume_user)
+GLOBAL_ENTRY(notify_resume_user)
         .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8)
         alloc loc1=ar.pfs,8,2,3,0 // preserve all eight input regs in case of syscall restart!
         mov r9=ar.unat
@@ -1306,7 +1334,7 @@ ENTRY(sys_rt_sigreturn)
         adds sp=16,sp
         ;;
         ld8 r9=[sp]                             // load new ar.unat
-        mov.sptk b7=r8,ia64_leave_kernel
+        mov.sptk b7=r8,ia64_native_leave_kernel
         ;;
         mov ar.unat=r9
         br.many b7
@@ -1665,3 +1693,4 @@ sys_call_table:
         data8 sys_timerfd_gettime
 
         .org sys_call_table + 8*NR_syscalls     // guard against failures to increase NR_syscalls
+#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index ddeab4e36fd5..db540e58c783 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -26,11 +26,14 @@
 #include <asm/mmu_context.h>
 #include <asm/asm-offsets.h>
 #include <asm/pal.h>
+#include <asm/paravirt.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
 #include <asm/mca_asm.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
 #define SAL_PSR_BITS_TO_SET                             \
@@ -367,6 +370,44 @@ start_ap:
         ;;
 (isBP)  st8 [r2]=r28            // save the address of the boot param area passed by the bootloader
 
+#ifdef CONFIG_PARAVIRT
+
+        movl r14=hypervisor_setup_hooks
+        movl r15=hypervisor_type
+        mov r16=num_hypervisor_hooks
+        ;;
+        ld8 r2=[r15]
+        ;;
+        cmp.ltu p7,p0=r2,r16    // array size check
+        shladd r8=r2,3,r14
+        ;;
+(p7)    ld8 r9=[r8]
+        ;;
+(p7)    mov b1=r9
+(p7)    cmp.ne.unc p7,p0=r9,r0  // no actual branch to NULL
+        ;;
+(p7)    br.call.sptk.many rp=b1
+
+        __INITDATA
+
+default_setup_hook = 0          // Currently nothing needs to be done.
+
+        .weak xen_setup_hook
+
+        .global hypervisor_type
+hypervisor_type:
+        data8           PARAVIRT_HYPERVISOR_TYPE_DEFAULT
+
+        // must have the same order with PARAVIRT_HYPERVISOR_TYPE_xxx
+
+hypervisor_setup_hooks:
+        data8           default_setup_hook
+        data8           xen_setup_hook
+num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8
+        .previous
+
+#endif
+
 #ifdef CONFIG_SMP
 (isAP)  br.call.sptk.many rp=start_secondary
 .ret0:
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 39752cdef6ff..3bc2fa64f87f 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -585,6 +585,15 @@ static inline int irq_is_shared (int irq)
         return (iosapic_intr_info[irq].count > 1);
 }
 
+struct irq_chip*
+ia64_native_iosapic_get_irq_chip(unsigned long trigger)
+{
+        if (trigger == IOSAPIC_EDGE)
+                return &irq_type_iosapic_edge;
+        else
+                return &irq_type_iosapic_level;
+}
+
 static int
 register_intr (unsigned int gsi, int irq, unsigned char delivery,
                unsigned long polarity, unsigned long trigger)
@@ -635,13 +644,10 @@ register_intr (unsigned int gsi, int irq, unsigned char delivery,
         iosapic_intr_info[irq].dmode    = delivery;
         iosapic_intr_info[irq].trigger  = trigger;
 
-        if (trigger == IOSAPIC_EDGE)
-                irq_type = &irq_type_iosapic_edge;
-        else
-                irq_type = &irq_type_iosapic_level;
+        irq_type = iosapic_get_irq_chip(trigger);
 
         idesc = irq_desc + irq;
-        if (idesc->chip != irq_type) {
+        if (irq_type != NULL && idesc->chip != irq_type) {
                 if (idesc->chip != &no_irq_type)
                         printk(KERN_WARNING
                                "%s: changing vector %d from %s to %s\n",
@@ -974,6 +980,22 @@ iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi,
 }
 
 void __init
+ia64_native_iosapic_pcat_compat_init(void)
+{
+        if (pcat_compat) {
+                /*
+                 * Disable the compatibility mode interrupts (8259 style),
+                 * needs IN/OUT support enabled.
+                 */
+                printk(KERN_INFO
+                       "%s: Disabling PC-AT compatible 8259 interrupts\n",
+                       __func__);
+                outb(0xff, 0xA1);
+                outb(0xff, 0x21);
+        }
+}
+
+void __init
 iosapic_system_init (int system_pcat_compat)
 {
         int irq;
@@ -987,17 +1009,8 @@ iosapic_system_init (int system_pcat_compat)
         }
 
         pcat_compat = system_pcat_compat;
-        if (pcat_compat) {
-                /*
-                 * Disable the compatibility mode interrupts (8259 style),
-                 * needs IN/OUT support enabled.
-                 */
-                printk(KERN_INFO
-                       "%s: Disabling PC-AT compatible 8259 interrupts\n",
-                       __func__);
-                outb(0xff, 0xA1);
-                outb(0xff, 0x21);
-        }
+        if (pcat_compat)
+                iosapic_pcat_compat_init();
 }
 
 static inline int
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 5538471e8d68..28d3d483db92 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -196,7 +196,7 @@ static void clear_irq_vector(int irq)
 }
 
 int
-assign_irq_vector (int irq)
+ia64_native_assign_irq_vector (int irq)
 {
         unsigned long flags;
         int vector, cpu;
@@ -222,7 +222,7 @@ assign_irq_vector (int irq)
 }
 
 void
-free_irq_vector (int vector)
+ia64_native_free_irq_vector (int vector)
 {
         if (vector < IA64_FIRST_DEVICE_VECTOR ||
             vector > IA64_LAST_DEVICE_VECTOR)
@@ -600,7 +600,6 @@ static irqreturn_t dummy_handler (int irq, void *dev_id)
 {
         BUG();
 }
-extern irqreturn_t handle_IPI (int irq, void *dev_id);
 
 static struct irqaction ipi_irqaction = {
         .handler =      handle_IPI,
@@ -623,7 +622,7 @@ static struct irqaction tlb_irqaction = {
 #endif
 
 void
-register_percpu_irq (ia64_vector vec, struct irqaction *action)
+ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action)
 {
         irq_desc_t *desc;
         unsigned int irq;
@@ -638,13 +637,21 @@ register_percpu_irq (ia64_vector vec, struct irqaction *action)
 }
 
 void __init
-init_IRQ (void)
+ia64_native_register_ipi(void)
 {
-        register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL);
 #ifdef CONFIG_SMP
         register_percpu_irq(IA64_IPI_VECTOR, &ipi_irqaction);
         register_percpu_irq(IA64_IPI_RESCHEDULE, &resched_irqaction);
         register_percpu_irq(IA64_IPI_LOCAL_TLB_FLUSH, &tlb_irqaction);
+#endif
+}
+
+void __init
+init_IRQ (void)
+{
+        ia64_register_ipi();
+        register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL);
+#ifdef CONFIG_SMP
 #if defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG)
         if (vector_domain_type != VECTOR_DOMAIN_NONE) {
                 BUG_ON(IA64_FIRST_DEVICE_VECTOR != IA64_IRQ_MOVE_VECTOR);
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index 80b44ea052d7..c39627df3cde 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -12,6 +12,14 @@
  *
  * 00/08/23 Asit Mallick <asit.k.mallick@intel.com> TLB handling for SMP
  * 00/12/20 David Mosberger-Tang <davidm@hpl.hp.com> DTLB/ITLB handler now uses virtual PT.
+ *
+ * Copyright (C) 2005 Hewlett-Packard Co
+ *      Dan Magenheimer <dan.magenheimer@hp.com>
+ *      Xen paravirtualization
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *                    pv_ops.
+ *      Yaozu (Eddie) Dong <eddie.dong@intel.com>
  */
 /*
  * This file defines the interruption vector table used by the CPU.
@@ -102,13 +110,13 @@ ENTRY(vhpt_miss)
          *      - the faulting virtual address uses unimplemented address bits
          *      - the faulting virtual address has no valid page table mapping
          */
-        mov r16=cr.ifa                          // get address that caused the TLB miss
+        MOV_FROM_IFA(r16)                       // get address that caused the TLB miss
 #ifdef CONFIG_HUGETLB_PAGE
         movl r18=PAGE_SHIFT
-        mov r25=cr.itir
+        MOV_FROM_ITIR(r25)
 #endif
         ;;
-        rsm psr.dt                              // use physical addressing for data
+        RSM_PSR_DT                              // use physical addressing for data
         mov r31=pr                              // save the predicate registers
         mov r19=IA64_KR(PT_BASE)                // get page table base address
         shl r21=r16,3                           // shift bit 60 into sign bit
@@ -168,21 +176,21 @@ ENTRY(vhpt_miss)
         dep r21=r19,r20,3,(PAGE_SHIFT-3)        // r21=pte_offset(pmd,addr)
         ;;
 (p7)    ld8 r18=[r21]                           // read *pte
-        mov r19=cr.isr                          // cr.isr bit 32 tells us if this is an insn miss
+        MOV_FROM_ISR(r19)                       // cr.isr bit 32 tells us if this is an insn miss
         ;;
 (p7)    tbit.z p6,p7=r18,_PAGE_P_BIT            // page present bit cleared?
-        mov r22=cr.iha                          // get the VHPT address that caused the TLB miss
+        MOV_FROM_IHA(r22)                       // get the VHPT address that caused the TLB miss
         ;;                                      // avoid RAW on p7
 (p7)    tbit.nz.unc p10,p11=r19,32              // is it an instruction TLB miss?
         dep r23=0,r20,0,PAGE_SHIFT              // clear low bits to get page address
         ;;
-(p10)   itc.i r18                               // insert the instruction TLB entry
-(p11)   itc.d r18                               // insert the data TLB entry
+        ITC_I_AND_D(p10, p11, r18, r24)         // insert the instruction TLB entry and
+                                                // insert the data TLB entry
 (p6)    br.cond.spnt.many page_fault            // handle bad address/page not present (page fault)
-        mov cr.ifa=r22
+        MOV_TO_IFA(r22, r24)
 
 #ifdef CONFIG_HUGETLB_PAGE
-(p8)    mov cr.itir=r25                         // change to default page-size for VHPT
+        MOV_TO_ITIR(p8, r25, r24)               // change to default page-size for VHPT
 #endif
 
         /*
@@ -192,7 +200,7 @@ ENTRY(vhpt_miss)
          */
         adds r24=__DIRTY_BITS_NO_ED|_PAGE_PL_0|_PAGE_AR_RW,r23
         ;;
-(p7)    itc.d r24
+        ITC_D(p7, r24, r25)
         ;;
 #ifdef CONFIG_SMP
         /*
@@ -234,7 +242,7 @@ ENTRY(vhpt_miss)
 #endif
 
         mov pr=r31,-1                           // restore predicate registers
-        rfi
+        RFI
 END(vhpt_miss)
 
         .org ia64_ivt+0x400
@@ -248,11 +256,11 @@ ENTRY(itlb_miss)
          * mode, walk the page table, and then re-execute the PTE read and
          * go on normally after that.
          */
-        mov r16=cr.ifa                          // get virtual address
+        MOV_FROM_IFA(r16)                       // get virtual address
         mov r29=b0                              // save b0
         mov r31=pr                              // save predicates
 .itlb_fault:
-        mov r17=cr.iha                          // get virtual address of PTE
+        MOV_FROM_IHA(r17)                       // get virtual address of PTE
         movl r30=1f                             // load nested fault continuation point
         ;;
 1:      ld8 r18=[r17]                           // read *pte
@@ -261,7 +269,7 @@ ENTRY(itlb_miss)
         tbit.z p6,p0=r18,_PAGE_P_BIT            // page present bit cleared?
 (p6)    br.cond.spnt page_fault
         ;;
-        itc.i r18
+        ITC_I(p0, r18, r19)
         ;;
 #ifdef CONFIG_SMP
         /*
@@ -278,7 +286,7 @@ ENTRY(itlb_miss)
 (p7)    ptc.l r16,r20
 #endif
         mov pr=r31,-1
-        rfi
+        RFI
 END(itlb_miss)
 
         .org ia64_ivt+0x0800
@@ -292,11 +300,11 @@ ENTRY(dtlb_miss)
          * mode, walk the page table, and then re-execute the PTE read and
          * go on normally after that.
          */
-        mov r16=cr.ifa                          // get virtual address
+        MOV_FROM_IFA(r16)                       // get virtual address
         mov r29=b0                              // save b0
         mov r31=pr                              // save predicates
 dtlb_fault:
-        mov r17=cr.iha                          // get virtual address of PTE
+        MOV_FROM_IHA(r17)                       // get virtual address of PTE
         movl r30=1f                             // load nested fault continuation point
         ;;
 1:      ld8 r18=[r17]                           // read *pte
@@ -305,7 +313,7 @@ dtlb_fault:
         tbit.z p6,p0=r18,_PAGE_P_BIT            // page present bit cleared?
 (p6)    br.cond.spnt page_fault
         ;;
-        itc.d r18
+        ITC_D(p0, r18, r19)
         ;;
 #ifdef CONFIG_SMP
         /*
@@ -322,7 +330,7 @@ dtlb_fault:
 (p7)    ptc.l r16,r20
 #endif
         mov pr=r31,-1
-        rfi
+        RFI
 END(dtlb_miss)
 
         .org ia64_ivt+0x0c00
@@ -330,9 +338,9 @@ END(dtlb_miss)
 // 0x0c00 Entry 3 (size 64 bundles) Alt ITLB (19)
 ENTRY(alt_itlb_miss)
         DBG_FAULT(3)
-        mov r16=cr.ifa          // get address that caused the TLB miss
+        MOV_FROM_IFA(r16)       // get address that caused the TLB miss
         movl r17=PAGE_KERNEL
-        mov r21=cr.ipsr
+        MOV_FROM_IPSR(p0, r21)
         movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
         mov r31=pr
         ;;
@@ -341,9 +349,9 @@ ENTRY(alt_itlb_miss)
         ;;
         cmp.gt p8,p0=6,r22                      // user mode
         ;;
-(p8)    thash r17=r16
+        THASH(p8, r17, r16, r23)
         ;;
-(p8)    mov cr.iha=r17
+        MOV_TO_IHA(p8, r17, r23)
 (p8)    mov r29=b0                              // save b0
 (p8)    br.cond.dptk .itlb_fault
 #endif
@@ -358,9 +366,9 @@ ENTRY(alt_itlb_miss)
         or r19=r19,r18          // set bit 4 (uncached) if the access was to region 6
 (p8)    br.cond.spnt page_fault
         ;;
-        itc.i r19               // insert the TLB entry
+        ITC_I(p0, r19, r18)     // insert the TLB entry
         mov pr=r31,-1
-        rfi
+        RFI
 END(alt_itlb_miss)
 
         .org ia64_ivt+0x1000
@@ -368,11 +376,11 @@ END(alt_itlb_miss)
 // 0x1000 Entry 4 (size 64 bundles) Alt DTLB (7,46)
 ENTRY(alt_dtlb_miss)
         DBG_FAULT(4)
-        mov r16=cr.ifa          // get address that caused the TLB miss
+        MOV_FROM_IFA(r16)       // get address that caused the TLB miss
         movl r17=PAGE_KERNEL
-        mov r20=cr.isr
+        MOV_FROM_ISR(r20)
         movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
-        mov r21=cr.ipsr
+        MOV_FROM_IPSR(p0, r21)
         mov r31=pr
         mov r24=PERCPU_ADDR
         ;;
@@ -381,9 +389,9 @@ ENTRY(alt_dtlb_miss)
         ;;
         cmp.gt p8,p0=6,r22                      // access to region 0-5
         ;;
-(p8)    thash r17=r16
+        THASH(p8, r17, r16, r25)
         ;;
-(p8)    mov cr.iha=r17
+        MOV_TO_IHA(p8, r17, r25)
 (p8)    mov r29=b0                              // save b0
 (p8)    br.cond.dptk dtlb_fault
 #endif
@@ -402,7 +410,7 @@ ENTRY(alt_dtlb_miss)
         tbit.nz p9,p0=r20,IA64_ISR_NA_BIT       // is non-access bit on?
         ;;
 (p10)   sub r19=r19,r26
-(p10)   mov cr.itir=r25
+        MOV_TO_ITIR(p10, r25, r24)
         cmp.ne p8,p0=r0,r23
 (p9)    cmp.eq.or.andcm p6,p7=IA64_ISR_CODE_LFETCH,r22  // check isr.code field
 (p12)   dep r17=-1,r17,4,1                      // set ma=UC for region 6 addr
@@ -411,11 +419,11 @@ ENTRY(alt_dtlb_miss)
         dep r21=-1,r21,IA64_PSR_ED_BIT,1
         ;;
         or r19=r19,r17          // insert PTE control bits into r19
-(p6)    mov cr.ipsr=r21
+        MOV_TO_IPSR(p6, r21, r24)
         ;;
-(p7)    itc.d r19               // insert the TLB entry
+        ITC_D(p7, r19, r18)     // insert the TLB entry
         mov pr=r31,-1
-        rfi
+        RFI
 END(alt_dtlb_miss)
 
         .org ia64_ivt+0x1400
@@ -444,10 +452,10 @@ ENTRY(nested_dtlb_miss)
          *
          * Clobbered:   b0, r18, r19, r21, r22, psr.dt (cleared)
          */
-        rsm psr.dt                              // switch to using physical data addressing
+        RSM_PSR_DT                              // switch to using physical data addressing
         mov r19=IA64_KR(PT_BASE)                // get the page table base address
         shl r21=r16,3                           // shift bit 60 into sign bit
-        mov r18=cr.itir
+        MOV_FROM_ITIR(r18)
         ;;
         shr.u r17=r16,61                        // get the region number into r17
         extr.u r18=r18,2,6                      // get the faulting page size
@@ -507,33 +515,6 @@ ENTRY(ikey_miss)
         FAULT(6)
 END(ikey_miss)
 
-        //-----------------------------------------------------------------------------------
-        // call do_page_fault (predicates are in r31, psr.dt may be off, r16 is faulting address)
-ENTRY(page_fault)
-        ssm psr.dt
-        ;;
-        srlz.i
-        ;;
-        SAVE_MIN_WITH_COVER
-        alloc r15=ar.pfs,0,0,3,0
-        mov out0=cr.ifa
-        mov out1=cr.isr
-        adds r3=8,r2                            // set up second base pointer
-        ;;
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i                                  // guarantee that interruption collectin is on
-        ;;
-(p15)   ssm psr.i                               // restore psr.i
-        movl r14=ia64_leave_kernel
-        ;;
-        SAVE_REST
-        mov rp=r14
-        ;;
-        adds out2=16,r12                        // out2 = pointer to pt_regs
-        br.call.sptk.many b6=ia64_do_page_fault // ignore return address
-END(page_fault)
-
         .org ia64_ivt+0x1c00
 /////////////////////////////////////////////////////////////////////////////////////////
 // 0x1c00 Entry 7 (size 64 bundles) Data Key Miss (12,51)
@@ -556,10 +537,10 @@ ENTRY(dirty_bit)
          * page table TLB entry isn't present, we take a nested TLB miss hit where we look
          * up the physical address of the L3 PTE and then continue at label 1 below.
          */
-        mov r16=cr.ifa                          // get the address that caused the fault
+        MOV_FROM_IFA(r16)                       // get the address that caused the fault
         movl r30=1f                             // load continuation point in case of nested fault
         ;;
-        thash r17=r16                           // compute virtual address of L3 PTE
+        THASH(p0, r17, r16, r18)                // compute virtual address of L3 PTE
         mov r29=b0                              // save b0 in case of nested fault
         mov r31=pr                              // save pr
 #ifdef CONFIG_SMP
@@ -576,7 +557,7 @@ ENTRY(dirty_bit)
         ;;
 (p6)    cmp.eq p6,p7=r26,r18                    // Only compare if page is present
         ;;
-(p6)    itc.d r25                               // install updated PTE
+        ITC_D(p6, r25, r18)                     // install updated PTE
         ;;
         /*
          * Tell the assemblers dependency-violation checker that the above "itc" instructions
@@ -602,7 +583,7 @@ ENTRY(dirty_bit)
         itc.d r18                               // install updated PTE
 #endif
         mov pr=r31,-1                           // restore pr
-        rfi
+        RFI
 END(dirty_bit)
 
         .org ia64_ivt+0x2400
@@ -611,22 +592,22 @@ END(dirty_bit)
 ENTRY(iaccess_bit)
         DBG_FAULT(9)
         // Like Entry 8, except for instruction access
-        mov r16=cr.ifa                          // get the address that caused the fault
+        MOV_FROM_IFA(r16)                       // get the address that caused the fault
         movl r30=1f                             // load continuation point in case of nested fault
         mov r31=pr                              // save predicates
 #ifdef CONFIG_ITANIUM
         /*
          * Erratum 10 (IFA may contain incorrect address) has "NoFix" status.
          */
-        mov r17=cr.ipsr
+        MOV_FROM_IPSR(p0, r17)
         ;;
-        mov r18=cr.iip
+        MOV_FROM_IIP(r18)
         tbit.z p6,p0=r17,IA64_PSR_IS_BIT        // IA64 instruction set?
         ;;
 (p6)    mov r16=r18                             // if so, use cr.iip instead of cr.ifa
 #endif /* CONFIG_ITANIUM */
         ;;
-        thash r17=r16                           // compute virtual address of L3 PTE
+        THASH(p0, r17, r16, r18)                // compute virtual address of L3 PTE
         mov r29=b0                              // save b0 in case of nested fault)
 #ifdef CONFIG_SMP
         mov r28=ar.ccv                          // save ar.ccv
@@ -642,7 +623,7 @@ ENTRY(iaccess_bit)
         ;;
 (p6)    cmp.eq p6,p7=r26,r18                    // Only if page present
         ;;
-(p6)    itc.i r25                               // install updated PTE
+        ITC_I(p6, r25, r26)                     // install updated PTE
         ;;
         /*
          * Tell the assemblers dependency-violation checker that the above "itc" instructions
@@ -668,7 +649,7 @@ ENTRY(iaccess_bit)
         itc.i r18                               // install updated PTE
 #endif /* !CONFIG_SMP */
         mov pr=r31,-1
-        rfi
+        RFI
 END(iaccess_bit)
 
         .org ia64_ivt+0x2800
@@ -677,10 +658,10 @@ END(iaccess_bit)
 ENTRY(daccess_bit)
         DBG_FAULT(10)
         // Like Entry 8, except for data access
-        mov r16=cr.ifa                          // get the address that caused the fault
+        MOV_FROM_IFA(r16)                       // get the address that caused the fault
         movl r30=1f                             // load continuation point in case of nested fault
         ;;
-        thash r17=r16                           // compute virtual address of L3 PTE
+        THASH(p0, r17, r16, r18)                // compute virtual address of L3 PTE
         mov r31=pr
         mov r29=b0                              // save b0 in case of nested fault)
 #ifdef CONFIG_SMP
@@ -697,7 +678,7 @@ ENTRY(daccess_bit)
         ;;
 (p6)    cmp.eq p6,p7=r26,r18                    // Only if page is present
         ;;
-(p6)    itc.d r25                               // install updated PTE
+        ITC_D(p6, r25, r26)                     // install updated PTE
         /*
          * Tell the assemblers dependency-violation checker that the above "itc" instructions
          * cannot possibly affect the following loads:
@@ -721,7 +702,7 @@ ENTRY(daccess_bit)
 #endif
         mov b0=r29                              // restore b0
         mov pr=r31,-1
-        rfi
+        RFI
 END(daccess_bit)
 
         .org ia64_ivt+0x2c00
@@ -745,10 +726,10 @@ ENTRY(break_fault)
          */
         DBG_FAULT(11)
         mov.m r16=IA64_KR(CURRENT)              // M2 r16 <- current task (12 cyc)
-        mov r29=cr.ipsr                         // M2 (12 cyc)
+        MOV_FROM_IPSR(p0, r29)                  // M2 (12 cyc)
         mov r31=pr                              // I0 (2 cyc)
 
-        mov r17=cr.iim                          // M2 (2 cyc)
+        MOV_FROM_IIM(r17)                       // M2 (2 cyc)
         mov.m r27=ar.rsc                        // M2 (12 cyc)
         mov r18=__IA64_BREAK_SYSCALL            // A
 
@@ -767,7 +748,7 @@ ENTRY(break_fault)
         nop.m 0
         movl r30=sys_call_table                 // X
 
-        mov r28=cr.iip                          // M2 (2 cyc)
+        MOV_FROM_IIP(r28)                       // M2 (2 cyc)
         cmp.eq p0,p7=r18,r17                    // I0 is this a system call?
 (p7)    br.cond.spnt non_syscall                // B  no ->
         //
@@ -864,18 +845,17 @@ ENTRY(break_fault)
 #endif
         mov ar.rsc=0x3                          // M2   set eager mode, pl 0, LE, loadrs=0
         nop 0
-        bsw.1                                   // B (6 cyc) regs are saved, switch to bank 1
+        BSW_1(r2, r14)                          // B (6 cyc) regs are saved, switch to bank 1
         ;;
 
-        ssm psr.ic | PSR_DEFAULT_BITS           // M2   now it's safe to re-enable intr.-collection
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, r16) // M2   now it's safe to re-enable intr.-collection
+                                                // M0   ensure interruption collection is on
         movl r3=ia64_ret_from_syscall           // X
         ;;
-
-        srlz.i                                  // M0   ensure interruption collection is on
         mov rp=r3                               // I0   set the real return addr
 (p10)   br.cond.spnt.many ia64_ret_from_syscall // B    return if bad call-frame or r15 is a NaT
 
-(p15)   ssm psr.i                               // M2   restore psr.i
+        SSM_PSR_I(p15, p15, r16)                // M2   restore psr.i
 (p14)   br.call.sptk.many b6=b6                 // B    invoke syscall-handker (ignore return addr)
         br.cond.spnt.many ia64_trace_syscall    // B    do syscall-tracing thingamagic
         // NOT REACHED
@@ -895,27 +875,8 @@ END(break_fault)
 /////////////////////////////////////////////////////////////////////////////////////////
 // 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
 ENTRY(interrupt)
-        DBG_FAULT(12)
-        mov r31=pr              // prepare to save predicates
-        ;;
-        SAVE_MIN_WITH_COVER     // uses r31; defines r2 and r3
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        adds r3=8,r2            // set up second base pointer for SAVE_REST
-        srlz.i                  // ensure everybody knows psr.ic is back on
-        ;;
-        SAVE_REST
-        ;;
-        MCA_RECOVER_RANGE(interrupt)
-        alloc r14=ar.pfs,0,0,2,0 // must be first in an insn group
-        mov out0=cr.ivr         // pass cr.ivr as first arg
-        add out1=16,sp          // pass pointer to pt_regs as second arg
-        ;;
-        srlz.d                  // make sure we see the effect of cr.ivr
-        movl r14=ia64_leave_kernel
-        ;;
-        mov rp=r14
-        br.call.sptk.many b6=ia64_handle_irq
+        /* interrupt handler has become too big to fit this area. */
+        br.sptk.many __interrupt
 END(interrupt)
 
         .org ia64_ivt+0x3400
@@ -978,6 +939,7 @@ END(interrupt)
          *      - ar.fpsr: set to kernel settings
          *      -  b6: preserved (same as on entry)
          */
+#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 GLOBAL_ENTRY(ia64_syscall_setup)
 #if PT(B6) != 0
 # error This code assumes that b6 is the first field in pt_regs.
@@ -1069,6 +1031,7 @@ GLOBAL_ENTRY(ia64_syscall_setup)
 (p10)   mov r8=-EINVAL
         br.ret.sptk.many b7
 END(ia64_syscall_setup)
+#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
         .org ia64_ivt+0x3c00
 /////////////////////////////////////////////////////////////////////////////////////////
@@ -1082,7 +1045,7 @@ END(ia64_syscall_setup)
         DBG_FAULT(16)
         FAULT(16)
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
         /*
          * There is no particular reason for this code to be here, other than
          * that there happens to be space here that would go unused otherwise.
@@ -1092,7 +1055,7 @@ END(ia64_syscall_setup)
          * account_sys_enter is called from SAVE_MIN* macros if accounting is
          * enabled and if the macro is entered from user mode.
          */
-ENTRY(account_sys_enter)
+GLOBAL_ENTRY(account_sys_enter)
         // mov.m r20=ar.itc is called in advance, and r13 is current
         add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13
         add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13
@@ -1123,110 +1086,18 @@ END(account_sys_enter)
         DBG_FAULT(17)
         FAULT(17)
 
-ENTRY(non_syscall)
-        mov ar.rsc=r27                  // restore ar.rsc before SAVE_MIN_WITH_COVER
-        ;;
-        SAVE_MIN_WITH_COVER
-
-        // There is no particular reason for this code to be here, other than that
-        // there happens to be space here that would go unused otherwise.  If this
-        // fault ever gets "unreserved", simply moved the following code to a more
-        // suitable spot...
-
-        alloc r14=ar.pfs,0,0,2,0
-        mov out0=cr.iim
-        add out1=16,sp
-        adds r3=8,r2                    // set up second base pointer for SAVE_REST
-
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i                          // guarantee that interruption collection is on
-        ;;
-(p15)   ssm psr.i                       // restore psr.i
-        movl r15=ia64_leave_kernel
-        ;;
-        SAVE_REST
-        mov rp=r15
-        ;;
-        br.call.sptk.many b6=ia64_bad_break     // avoid WAW on CFM and ignore return addr
-END(non_syscall)
-
         .org ia64_ivt+0x4800
 /////////////////////////////////////////////////////////////////////////////////////////
 // 0x4800 Entry 18 (size 64 bundles) Reserved
         DBG_FAULT(18)
         FAULT(18)
 
-        /*
-         * There is no particular reason for this code to be here, other than that
-         * there happens to be space here that would go unused otherwise.  If this
-         * fault ever gets "unreserved", simply moved the following code to a more
-         * suitable spot...
-         */
-
-ENTRY(dispatch_unaligned_handler)
-        SAVE_MIN_WITH_COVER
-        ;;
-        alloc r14=ar.pfs,0,0,2,0                // now it's safe (must be first in insn group!)
-        mov out0=cr.ifa
-        adds out1=16,sp
-
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i                                  // guarantee that interruption collection is on
-        ;;
-(p15)   ssm psr.i                               // restore psr.i
-        adds r3=8,r2                            // set up second base pointer
-        ;;
-        SAVE_REST
-        movl r14=ia64_leave_kernel
-        ;;
-        mov rp=r14
-        br.sptk.many ia64_prepare_handle_unaligned
-END(dispatch_unaligned_handler)
-
         .org ia64_ivt+0x4c00
 /////////////////////////////////////////////////////////////////////////////////////////
 // 0x4c00 Entry 19 (size 64 bundles) Reserved
         DBG_FAULT(19)
         FAULT(19)
 
-        /*
-         * There is no particular reason for this code to be here, other than that
-         * there happens to be space here that would go unused otherwise.  If this
-         * fault ever gets "unreserved", simply moved the following code to a more
-         * suitable spot...
-         */
-
-ENTRY(dispatch_to_fault_handler)
-        /*
-         * Input:
-         *      psr.ic: off
-         *      r19:    fault vector number (e.g., 24 for General Exception)
-         *      r31:    contains saved predicates (pr)
-         */
-        SAVE_MIN_WITH_COVER_R19
-        alloc r14=ar.pfs,0,0,5,0
-        mov out0=r15
-        mov out1=cr.isr
-        mov out2=cr.ifa
-        mov out3=cr.iim
-        mov out4=cr.itir
-        ;;
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i                                  // guarantee that interruption collection is on
-        ;;
-(p15)   ssm psr.i                               // restore psr.i
-        adds r3=8,r2                            // set up second base pointer for SAVE_REST
-        ;;
-        SAVE_REST
-        movl r14=ia64_leave_kernel
-        ;;
-        mov rp=r14
-        br.call.sptk.many b6=ia64_fault
-END(dispatch_to_fault_handler)
-
 //
 // --- End of long entries, Beginning of short entries
 //
@@ -1236,8 +1107,8 @@ END(dispatch_to_fault_handler)
 // 0x5000 Entry 20 (size 16 bundles) Page Not Present (10,22,49)
 ENTRY(page_not_present)
         DBG_FAULT(20)
-        mov r16=cr.ifa
-        rsm psr.dt
+        MOV_FROM_IFA(r16)
+        RSM_PSR_DT
         /*
          * The Linux page fault handler doesn't expect non-present pages to be in
          * the TLB.  Flush the existing entry now, so we meet that expectation.
@@ -1256,8 +1127,8 @@ END(page_not_present)
 // 0x5100 Entry 21 (size 16 bundles) Key Permission (13,25,52)
 ENTRY(key_permission)
         DBG_FAULT(21)
-        mov r16=cr.ifa
-        rsm psr.dt
+        MOV_FROM_IFA(r16)
+        RSM_PSR_DT
         mov r31=pr
         ;;
         srlz.d
@@ -1269,8 +1140,8 @@ END(key_permission)
 // 0x5200 Entry 22 (size 16 bundles) Instruction Access Rights (26)
 ENTRY(iaccess_rights)
         DBG_FAULT(22)
-        mov r16=cr.ifa
-        rsm psr.dt
+        MOV_FROM_IFA(r16)
+        RSM_PSR_DT
         mov r31=pr
         ;;
         srlz.d
@@ -1282,8 +1153,8 @@ END(iaccess_rights)
 // 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53)
 ENTRY(daccess_rights)
         DBG_FAULT(23)
-        mov r16=cr.ifa
-        rsm psr.dt
+        MOV_FROM_IFA(r16)
+        RSM_PSR_DT
         mov r31=pr
         ;;
         srlz.d
@@ -1295,7 +1166,7 @@ END(daccess_rights)
 // 0x5400 Entry 24 (size 16 bundles) General Exception (5,32,34,36,38,39)
 ENTRY(general_exception)
         DBG_FAULT(24)
-        mov r16=cr.isr
+        MOV_FROM_ISR(r16)
         mov r31=pr
         ;;
         cmp4.eq p6,p0=0,r16
@@ -1324,8 +1195,8 @@ END(disabled_fp_reg)
 ENTRY(nat_consumption)
         DBG_FAULT(26)
 
-        mov r16=cr.ipsr
-        mov r17=cr.isr
+        MOV_FROM_IPSR(p0, r16)
+        MOV_FROM_ISR(r17)
         mov r31=pr                              // save PR
         ;;
         and r18=0xf,r17                         // r18 = cr.ipsr.code{3:0}
@@ -1335,10 +1206,10 @@ ENTRY(nat_consumption)
         dep r16=-1,r16,IA64_PSR_ED_BIT,1
 (p6)    br.cond.spnt 1f         // branch if (cr.ispr.na == 0 || cr.ipsr.code{3:0} != LFETCH)
         ;;
-        mov cr.ipsr=r16         // set cr.ipsr.na
+        MOV_TO_IPSR(p0, r16, r18)
         mov pr=r31,-1
         ;;
-        rfi
+        RFI
 
 1:      mov pr=r31,-1
         ;;
@@ -1360,26 +1231,26 @@ ENTRY(speculation_vector)
          *
          * cr.imm contains zero_ext(imm21)
          */
-        mov r18=cr.iim
+        MOV_FROM_IIM(r18)
         ;;
-        mov r17=cr.iip
+        MOV_FROM_IIP(r17)
         shl r18=r18,43                  // put sign bit in position (43=64-21)
         ;;
 
-        mov r16=cr.ipsr
+        MOV_FROM_IPSR(p0, r16)
         shr r18=r18,39                  // sign extend (39=43-4)
         ;;
 
         add r17=r17,r18                 // now add the offset
         ;;
-        mov cr.iip=r17
+        MOV_FROM_IIP(r17)
         dep r16=0,r16,41,2              // clear EI
         ;;
 
-        mov cr.ipsr=r16
+        MOV_FROM_IPSR(p0, r16)
         ;;
 
-        rfi                             // and go back
+        RFI
 END(speculation_vector)
 
         .org ia64_ivt+0x5800
@@ -1517,11 +1388,11 @@ ENTRY(ia32_intercept)
         DBG_FAULT(46)
 #ifdef  CONFIG_IA32_SUPPORT
         mov r31=pr
-        mov r16=cr.isr
+        MOV_FROM_ISR(r16)
         ;;
         extr.u r17=r16,16,8     // get ISR.code
         mov r18=ar.eflag
-        mov r19=cr.iim          // old eflag value
+        MOV_FROM_IIM(r19)       // old eflag value
         ;;
         cmp.ne p6,p0=2,r17
 (p6)    br.cond.spnt 1f         // not a system flag fault
@@ -1533,7 +1404,7 @@ ENTRY(ia32_intercept)
 (p6)    br.cond.spnt 1f         // eflags.ac bit didn't change
         ;;
         mov pr=r31,-1           // restore predicate registers
-        rfi
+        RFI
 
 1:
 #endif  // CONFIG_IA32_SUPPORT
@@ -1673,6 +1544,137 @@ END(ia32_interrupt)
         DBG_FAULT(67)
         FAULT(67)
 
+        //-----------------------------------------------------------------------------------
+        // call do_page_fault (predicates are in r31, psr.dt may be off, r16 is faulting address)
+ENTRY(page_fault)
+        SSM_PSR_DT_AND_SRLZ_I
+        ;;
+        SAVE_MIN_WITH_COVER
+        alloc r15=ar.pfs,0,0,3,0
+        MOV_FROM_IFA(out0)
+        MOV_FROM_ISR(out1)
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r14, r3)
+        adds r3=8,r2                            // set up second base pointer
+        SSM_PSR_I(p15, p15, r14)                // restore psr.i
+        movl r14=ia64_leave_kernel
+        ;;
+        SAVE_REST
+        mov rp=r14
+        ;;
+        adds out2=16,r12                        // out2 = pointer to pt_regs
+        br.call.sptk.many b6=ia64_do_page_fault // ignore return address
+END(page_fault)
+
+ENTRY(non_syscall)
+        mov ar.rsc=r27                  // restore ar.rsc before SAVE_MIN_WITH_COVER
+        ;;
+        SAVE_MIN_WITH_COVER
+
+        // There is no particular reason for this code to be here, other than that
+        // there happens to be space here that would go unused otherwise.  If this
+        // fault ever gets "unreserved", simply moved the following code to a more
+        // suitable spot...
+
+        alloc r14=ar.pfs,0,0,2,0
+        MOV_FROM_IIM(out0)
+        add out1=16,sp
+        adds r3=8,r2                    // set up second base pointer for SAVE_REST
+
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r15, r24)
+                                        // guarantee that interruption collection is on
+        SSM_PSR_I(p15, p15, r15)        // restore psr.i
+        movl r15=ia64_leave_kernel
+        ;;
+        SAVE_REST
+        mov rp=r15
+        ;;
+        br.call.sptk.many b6=ia64_bad_break     // avoid WAW on CFM and ignore return addr
+END(non_syscall)
+
+ENTRY(__interrupt)
+        DBG_FAULT(12)
+        mov r31=pr              // prepare to save predicates
+        ;;
+        SAVE_MIN_WITH_COVER     // uses r31; defines r2 and r3
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, r14)
+                                // ensure everybody knows psr.ic is back on
+        adds r3=8,r2            // set up second base pointer for SAVE_REST
+        ;;
+        SAVE_REST
+        ;;
+        MCA_RECOVER_RANGE(interrupt)
+        alloc r14=ar.pfs,0,0,2,0 // must be first in an insn group
+        MOV_FROM_IVR(out0, r8)  // pass cr.ivr as first arg
+        add out1=16,sp          // pass pointer to pt_regs as second arg
+        ;;
+        srlz.d                  // make sure we see the effect of cr.ivr
+        movl r14=ia64_leave_kernel
+        ;;
+        mov rp=r14
+        br.call.sptk.many b6=ia64_handle_irq
+END(__interrupt)
+
+        /*
+         * There is no particular reason for this code to be here, other than that
+         * there happens to be space here that would go unused otherwise.  If this
+         * fault ever gets "unreserved", simply moved the following code to a more
+         * suitable spot...
+         */
+
+ENTRY(dispatch_unaligned_handler)
+        SAVE_MIN_WITH_COVER
+        ;;
+        alloc r14=ar.pfs,0,0,2,0                // now it's safe (must be first in insn group!)
+        MOV_FROM_IFA(out0)
+        adds out1=16,sp
+
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, r24)
+                                                // guarantee that interruption collection is on
+        SSM_PSR_I(p15, p15, r3)                 // restore psr.i
+        adds r3=8,r2                            // set up second base pointer
+        ;;
+        SAVE_REST
+        movl r14=ia64_leave_kernel
+        ;;
+        mov rp=r14
+        br.sptk.many ia64_prepare_handle_unaligned
+END(dispatch_unaligned_handler)
+
+        /*
+         * There is no particular reason for this code to be here, other than that
+         * there happens to be space here that would go unused otherwise.  If this
+         * fault ever gets "unreserved", simply moved the following code to a more
+         * suitable spot...
+         */
+
+ENTRY(dispatch_to_fault_handler)
+        /*
+         * Input:
+         *      psr.ic: off
+         *      r19:    fault vector number (e.g., 24 for General Exception)
+         *      r31:    contains saved predicates (pr)
+         */
+        SAVE_MIN_WITH_COVER_R19
+        alloc r14=ar.pfs,0,0,5,0
+        MOV_FROM_ISR(out1)
+        MOV_FROM_IFA(out2)
+        MOV_FROM_IIM(out3)
+        MOV_FROM_ITIR(out4)
+        ;;
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, out0)
+                                                // guarantee that interruption collection is on
+        mov out0=r15
+        ;;
+        SSM_PSR_I(p15, p15, r3)                 // restore psr.i
+        adds r3=8,r2                            // set up second base pointer for SAVE_REST
+        ;;
+        SAVE_REST
+        movl r14=ia64_leave_kernel
+        ;;
+        mov rp=r14
+        br.call.sptk.many b6=ia64_fault
+END(dispatch_to_fault_handler)
+
         /*
          * Squatting in this space ...
          *
@@ -1686,11 +1688,10 @@ ENTRY(dispatch_illegal_op_fault)
         .prologue
         .body
         SAVE_MIN_WITH_COVER
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i          // guarantee that interruption collection is on
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, r24)
+                                // guarantee that interruption collection is on
         ;;
-(p15)   ssm psr.i       // restore psr.i
+        SSM_PSR_I(p15, p15, r3) // restore psr.i
         adds r3=8,r2    // set up second base pointer for SAVE_REST
         ;;
         alloc r14=ar.pfs,0,0,1,0        // must be first in insn group
@@ -1729,12 +1730,11 @@ END(dispatch_illegal_op_fault)
 ENTRY(dispatch_to_ia32_handler)
         SAVE_MIN
         ;;
-        mov r14=cr.isr
-        ssm psr.ic | PSR_DEFAULT_BITS
-        ;;
-        srlz.i                                  // guarantee that interruption collection is on
+        MOV_FROM_ISR(r14)
+        SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(r3, r24)
+                                // guarantee that interruption collection is on
         ;;
-(p15)   ssm psr.i
+        SSM_PSR_I(p15, p15, r3)
         adds r3=8,r2            // Base pointer for SAVE_REST
         ;;
         SAVE_REST
diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h
index 74b6d670aaef..292e214a3b84 100644
--- a/arch/ia64/kernel/minstate.h
+++ b/arch/ia64/kernel/minstate.h
@@ -2,6 +2,7 @@
 #include <asm/cache.h>
 
 #include "entry.h"
+#include "paravirt_inst.h"
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /* read ar.itc in advance, and use it before leaving bank 0 */
@@ -43,16 +44,16 @@
  * Note that psr.ic is NOT turned on by this macro.  This is so that
  * we can pass interruption state as arguments to a handler.
  */
-#define DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA,WORKAROUND)                                            \
+#define IA64_NATIVE_DO_SAVE_MIN(__COVER,SAVE_IFS,EXTRA,WORKAROUND)                              \
         mov r16=IA64_KR(CURRENT);       /* M */                                                 \
         mov r27=ar.rsc;                 /* M */                                                 \
         mov r20=r1;                     /* A */                                                 \
         mov r25=ar.unat;                /* M */                                                 \
-        mov r29=cr.ipsr;                /* M */                                                 \
+        MOV_FROM_IPSR(p0,r29);          /* M */                                                 \
         mov r26=ar.pfs;                 /* I */                                                 \
-        mov r28=cr.iip;                 /* M */                                                 \
+        MOV_FROM_IIP(r28);                      /* M */                                         \
         mov r21=ar.fpsr;                /* M */                                                 \
-        COVER;                          /* B;; (or nothing) */                                  \
+        __COVER;                                /* B;; (or nothing) */                          \
         ;;                                                                                      \
         adds r16=IA64_TASK_THREAD_ON_USTACK_OFFSET,r16;                                         \
         ;;                                                                                      \
@@ -244,6 +245,6 @@
 1:                                              \
         .pred.rel "mutex", pKStk, pUStk
 
-#define SAVE_MIN_WITH_COVER     DO_SAVE_MIN(cover, mov r30=cr.ifs, , RSE_WORKAROUND)
-#define SAVE_MIN_WITH_COVER_R19 DO_SAVE_MIN(cover, mov r30=cr.ifs, mov r15=r19, RSE_WORKAROUND)
+#define SAVE_MIN_WITH_COVER     DO_SAVE_MIN(COVER, mov r30=cr.ifs, , RSE_WORKAROUND)
+#define SAVE_MIN_WITH_COVER_R19 DO_SAVE_MIN(COVER, mov r30=cr.ifs, mov r15=r19, RSE_WORKAROUND)
 #define SAVE_MIN                        DO_SAVE_MIN(     , mov r30=r0, , )
diff --git a/arch/ia64/kernel/nr-irqs.c b/arch/ia64/kernel/nr-irqs.c
new file mode 100644
index 000000000000..1ae049181e83
--- /dev/null
+++ b/arch/ia64/kernel/nr-irqs.c
@@ -0,0 +1,24 @@
+/*
+ * calculate
+ * NR_IRQS = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, FOO_NR_IRQS...)
+ * depending on config.
+ * This must be calculated before processing asm-offset.c.
+ */
+
+#define ASM_OFFSETS_C 1
+
+#include <linux/kbuild.h>
+#include <linux/threads.h>
+#include <asm-ia64/native/irq.h>
+
+void foo(void)
+{
+        union paravirt_nr_irqs_max {
+                char ia64_native_nr_irqs[IA64_NATIVE_NR_IRQS];
+#ifdef CONFIG_XEN
+                char xen_nr_irqs[XEN_NR_IRQS];
+#endif
+        };
+
+        DEFINE(NR_IRQS, sizeof (union paravirt_nr_irqs_max));
+}
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
new file mode 100644
index 000000000000..afaf5b9a2cf0
--- /dev/null
+++ b/arch/ia64/kernel/paravirt.c
@@ -0,0 +1,369 @@
+/******************************************************************************
+ * arch/ia64/kernel/paravirt.c
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *     Yaozu (Eddie) Dong <eddie.dong@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/init.h>
+
+#include <linux/compiler.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include <asm/iosapic.h>
+#include <asm/paravirt.h>
+
+/***************************************************************************
+ * general info
+ */
+struct pv_info pv_info = {
+        .kernel_rpl = 0,
+        .paravirt_enabled = 0,
+        .name = "bare hardware"
+};
+
+/***************************************************************************
+ * pv_init_ops
+ * initialization hooks.
+ */
+
+struct pv_init_ops pv_init_ops;
+
+/***************************************************************************
+ * pv_cpu_ops
+ * intrinsics hooks.
+ */
+
+/* ia64_native_xxx are macros so that we have to make them real functions */
+
+#define DEFINE_VOID_FUNC1(name)                                 \
+        static void                                             \
+        ia64_native_ ## name ## _func(unsigned long arg)        \
+        {                                                       \
+                ia64_native_ ## name(arg);                      \
+        }                                                       \
+
+#define DEFINE_VOID_FUNC2(name)                                 \
+        static void                                             \
+        ia64_native_ ## name ## _func(unsigned long arg0,       \
+                                      unsigned long arg1)       \
+        {                                                       \
+                ia64_native_ ## name(arg0, arg1);               \
+        }                                                       \
+
+#define DEFINE_FUNC0(name)                      \
+        static unsigned long                    \
+        ia64_native_ ## name ## _func(void)     \
+        {                                       \
+                return ia64_native_ ## name();  \
+        }
+
+#define DEFINE_FUNC1(name, type)                        \
+        static unsigned long                            \
+        ia64_native_ ## name ## _func(type arg)         \
+        {                                               \
+                return ia64_native_ ## name(arg);       \
+        }                                               \
+
+DEFINE_VOID_FUNC1(fc);
+DEFINE_VOID_FUNC1(intrin_local_irq_restore);
+
+DEFINE_VOID_FUNC2(ptcga);
+DEFINE_VOID_FUNC2(set_rr);
+
+DEFINE_FUNC0(get_psr_i);
+
+DEFINE_FUNC1(thash, unsigned long);
+DEFINE_FUNC1(get_cpuid, int);
+DEFINE_FUNC1(get_pmd, int);
+DEFINE_FUNC1(get_rr, unsigned long);
+
+static void
+ia64_native_ssm_i_func(void)
+{
+        ia64_native_ssm(IA64_PSR_I);
+}
+
+static void
+ia64_native_rsm_i_func(void)
+{
+        ia64_native_rsm(IA64_PSR_I);
+}
+
+static void
+ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
+                                unsigned long val2, unsigned long val3,
+                                unsigned long val4)
+{
+        ia64_native_set_rr0_to_rr4(val0, val1, val2, val3, val4);
+}
+
+#define CASE_GET_REG(id)                                \
+        case _IA64_REG_ ## id:                          \
+        res = ia64_native_getreg(_IA64_REG_ ## id);     \
+        break;
+#define CASE_GET_AR(id) CASE_GET_REG(AR_ ## id)
+#define CASE_GET_CR(id) CASE_GET_REG(CR_ ## id)
+
+unsigned long
+ia64_native_getreg_func(int regnum)
+{
+        unsigned long res = -1;
+        switch (regnum) {
+        CASE_GET_REG(GP);
+        CASE_GET_REG(IP);
+        CASE_GET_REG(PSR);
+        CASE_GET_REG(TP);
+        CASE_GET_REG(SP);
+
+        CASE_GET_AR(KR0);
+        CASE_GET_AR(KR1);
+        CASE_GET_AR(KR2);
+        CASE_GET_AR(KR3);
+        CASE_GET_AR(KR4);
+        CASE_GET_AR(KR5);
+        CASE_GET_AR(KR6);
+        CASE_GET_AR(KR7);
+        CASE_GET_AR(RSC);
+        CASE_GET_AR(BSP);
+        CASE_GET_AR(BSPSTORE);
+        CASE_GET_AR(RNAT);
+        CASE_GET_AR(FCR);
+        CASE_GET_AR(EFLAG);
+        CASE_GET_AR(CSD);
+        CASE_GET_AR(SSD);
+        CASE_GET_AR(CFLAG);
+        CASE_GET_AR(FSR);
+        CASE_GET_AR(FIR);
+        CASE_GET_AR(FDR);
+        CASE_GET_AR(CCV);
+        CASE_GET_AR(UNAT);
+        CASE_GET_AR(FPSR);
+        CASE_GET_AR(ITC);
+        CASE_GET_AR(PFS);
+        CASE_GET_AR(LC);
+        CASE_GET_AR(EC);
+
+        CASE_GET_CR(DCR);
+        CASE_GET_CR(ITM);
+        CASE_GET_CR(IVA);
+        CASE_GET_CR(PTA);
+        CASE_GET_CR(IPSR);
+        CASE_GET_CR(ISR);
+        CASE_GET_CR(IIP);
+        CASE_GET_CR(IFA);
+        CASE_GET_CR(ITIR);
+        CASE_GET_CR(IIPA);
+        CASE_GET_CR(IFS);
+        CASE_GET_CR(IIM);
+        CASE_GET_CR(IHA);
+        CASE_GET_CR(LID);
+        CASE_GET_CR(IVR);
+        CASE_GET_CR(TPR);
+        CASE_GET_CR(EOI);
+        CASE_GET_CR(IRR0);
+        CASE_GET_CR(IRR1);
+        CASE_GET_CR(IRR2);
+        CASE_GET_CR(IRR3);
+        CASE_GET_CR(ITV);
+        CASE_GET_CR(PMV);
+        CASE_GET_CR(CMCV);
+        CASE_GET_CR(LRR0);
+        CASE_GET_CR(LRR1);
+
+        default:
+                printk(KERN_CRIT "wrong_getreg %d\n", regnum);
+                break;
+        }
+        return res;
+}
+
+#define CASE_SET_REG(id)                                \
+        case _IA64_REG_ ## id:                          \
+        ia64_native_setreg(_IA64_REG_ ## id, val);      \
+        break;
+#define CASE_SET_AR(id) CASE_SET_REG(AR_ ## id)
+#define CASE_SET_CR(id) CASE_SET_REG(CR_ ## id)
+
+void
+ia64_native_setreg_func(int regnum, unsigned long val)
+{
+        switch (regnum) {
+        case _IA64_REG_PSR_L:
+                ia64_native_setreg(_IA64_REG_PSR_L, val);
+                ia64_dv_serialize_data();
+                break;
+        CASE_SET_REG(SP);
+        CASE_SET_REG(GP);
+
+        CASE_SET_AR(KR0);
+        CASE_SET_AR(KR1);
+        CASE_SET_AR(KR2);
+        CASE_SET_AR(KR3);
+        CASE_SET_AR(KR4);
+        CASE_SET_AR(KR5);
+        CASE_SET_AR(KR6);
+        CASE_SET_AR(KR7);
+        CASE_SET_AR(RSC);
+        CASE_SET_AR(BSP);
+        CASE_SET_AR(BSPSTORE);
+        CASE_SET_AR(RNAT);
+        CASE_SET_AR(FCR);
+        CASE_SET_AR(EFLAG);
+        CASE_SET_AR(CSD);
+        CASE_SET_AR(SSD);
+        CASE_SET_AR(CFLAG);
+        CASE_SET_AR(FSR);
+        CASE_SET_AR(FIR);
+        CASE_SET_AR(FDR);
+        CASE_SET_AR(CCV);
+        CASE_SET_AR(UNAT);
+        CASE_SET_AR(FPSR);
+        CASE_SET_AR(ITC);
+        CASE_SET_AR(PFS);
+        CASE_SET_AR(LC);
+        CASE_SET_AR(EC);
+
+        CASE_SET_CR(DCR);
+        CASE_SET_CR(ITM);
+        CASE_SET_CR(IVA);
+        CASE_SET_CR(PTA);
+        CASE_SET_CR(IPSR);
+        CASE_SET_CR(ISR);
+        CASE_SET_CR(IIP);
+        CASE_SET_CR(IFA);
+        CASE_SET_CR(ITIR);
+        CASE_SET_CR(IIPA);
+        CASE_SET_CR(IFS);
+        CASE_SET_CR(IIM);
+        CASE_SET_CR(IHA);
+        CASE_SET_CR(LID);
+        CASE_SET_CR(IVR);
+        CASE_SET_CR(TPR);
+        CASE_SET_CR(EOI);
+        CASE_SET_CR(IRR0);
+        CASE_SET_CR(IRR1);
+        CASE_SET_CR(IRR2);
+        CASE_SET_CR(IRR3);
+        CASE_SET_CR(ITV);
+        CASE_SET_CR(PMV);
+        CASE_SET_CR(CMCV);
+        CASE_SET_CR(LRR0);
+        CASE_SET_CR(LRR1);
+        default:
+                printk(KERN_CRIT "wrong setreg %d\n", regnum);
+                break;
+        }
+}
+
+struct pv_cpu_ops pv_cpu_ops = {
+        .fc             = ia64_native_fc_func,
+        .thash          = ia64_native_thash_func,
+        .get_cpuid      = ia64_native_get_cpuid_func,
+        .get_pmd        = ia64_native_get_pmd_func,
+        .ptcga          = ia64_native_ptcga_func,
+        .get_rr         = ia64_native_get_rr_func,
+        .set_rr         = ia64_native_set_rr_func,
+        .set_rr0_to_rr4 = ia64_native_set_rr0_to_rr4_func,
+        .ssm_i          = ia64_native_ssm_i_func,
+        .getreg         = ia64_native_getreg_func,
+        .setreg         = ia64_native_setreg_func,
+        .rsm_i          = ia64_native_rsm_i_func,
+        .get_psr_i      = ia64_native_get_psr_i_func,
+        .intrin_local_irq_restore
+                        = ia64_native_intrin_local_irq_restore_func,
+};
+EXPORT_SYMBOL(pv_cpu_ops);
+
+/******************************************************************************
+ * replacement of hand written assembly codes.
+ */
+
+void
+paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch)
+{
+        extern unsigned long paravirt_switch_to_targ;
+        extern unsigned long paravirt_leave_syscall_targ;
+        extern unsigned long paravirt_work_processed_syscall_targ;
+        extern unsigned long paravirt_leave_kernel_targ;
+
+        paravirt_switch_to_targ = cpu_asm_switch->switch_to;
+        paravirt_leave_syscall_targ = cpu_asm_switch->leave_syscall;
+        paravirt_work_processed_syscall_targ =
+                cpu_asm_switch->work_processed_syscall;
+        paravirt_leave_kernel_targ = cpu_asm_switch->leave_kernel;
+}
+
+/***************************************************************************
+ * pv_iosapic_ops
+ * iosapic read/write hooks.
+ */
+
+static unsigned int
+ia64_native_iosapic_read(char __iomem *iosapic, unsigned int reg)
+{
+        return __ia64_native_iosapic_read(iosapic, reg);
+}
+
+static void
+ia64_native_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
+{
+        __ia64_native_iosapic_write(iosapic, reg, val);
+}
+
+struct pv_iosapic_ops pv_iosapic_ops = {
+        .pcat_compat_init = ia64_native_iosapic_pcat_compat_init,
+        .get_irq_chip = ia64_native_iosapic_get_irq_chip,
+
+        .__read = ia64_native_iosapic_read,
+        .__write = ia64_native_iosapic_write,
+};
+
+/***************************************************************************
+ * pv_irq_ops
+ * irq operations
+ */
+
+struct pv_irq_ops pv_irq_ops = {
+        .register_ipi = ia64_native_register_ipi,
+
+        .assign_irq_vector = ia64_native_assign_irq_vector,
+        .free_irq_vector = ia64_native_free_irq_vector,
+        .register_percpu_irq = ia64_native_register_percpu_irq,
+
+        .resend_irq = ia64_native_resend_irq,
+};
+
+/***************************************************************************
+ * pv_time_ops
+ * time operations
+ */
+
+static int
+ia64_native_do_steal_accounting(unsigned long *new_itm)
+{
+        return 0;
+}
+
+struct pv_time_ops pv_time_ops = {
+        .do_steal_accounting = ia64_native_do_steal_accounting,
+};
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
new file mode 100644
index 000000000000..5cad6fb2ed19
--- /dev/null
+++ b/arch/ia64/kernel/paravirt_inst.h
@@ -0,0 +1,29 @@
+/******************************************************************************
+ * linux/arch/ia64/xen/paravirt_inst.h
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#ifdef __IA64_ASM_PARAVIRTUALIZED_XEN
+#include <asm/xen/inst.h>
+#include <asm/xen/minstate.h>
+#else
+#include <asm/native/inst.h>
+#endif
+
diff --git a/arch/ia64/kernel/paravirtentry.S b/arch/ia64/kernel/paravirtentry.S
new file mode 100644
index 000000000000..2f42fcb9776a
--- /dev/null
+++ b/arch/ia64/kernel/paravirtentry.S
@@ -0,0 +1,60 @@
+/******************************************************************************
+ * linux/arch/ia64/xen/paravirtentry.S
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <asm/asmmacro.h>
+#include <asm/asm-offsets.h>
+#include "entry.h"
+
+#define DATA8(sym, init_value)                  \
+        .pushsection .data.read_mostly ;        \
+        .align 8 ;                              \
+        .global sym ;                           \
+        sym: ;                                  \
+        data8 init_value ;                      \
+        .popsection
+
+#define BRANCH(targ, reg, breg)         \
+        movl reg=targ ;                 \
+        ;;                              \
+        ld8 reg=[reg] ;                 \
+        ;;                              \
+        mov breg=reg ;                  \
+        br.cond.sptk.many breg
+
+#define BRANCH_PROC(sym, reg, breg)                             \
+        DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
+        GLOBAL_ENTRY(paravirt_ ## sym) ;                        \
+                BRANCH(paravirt_ ## sym ## _targ, reg, breg) ;  \
+        END(paravirt_ ## sym)
+
+#define BRANCH_PROC_UNWINFO(sym, reg, breg)                     \
+        DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
+        GLOBAL_ENTRY(paravirt_ ## sym) ;                        \
+                PT_REGS_UNWIND_INFO(0) ;                        \
+                BRANCH(paravirt_ ## sym ## _targ, reg, breg) ;  \
+        END(paravirt_ ## sym)
+
+
+BRANCH_PROC(switch_to, r22, b7)
+BRANCH_PROC_UNWINFO(leave_syscall, r22, b7)
+BRANCH_PROC(work_processed_syscall, r2, b7)
+BRANCH_PROC_UNWINFO(leave_kernel, r22, b7)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 632cda8f2e76..e5c2de9b29a5 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -51,6 +51,7 @@
 #include <asm/mca.h>
 #include <asm/meminit.h>
 #include <asm/page.h>
+#include <asm/paravirt.h>
 #include <asm/patch.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -341,6 +342,8 @@ reserve_memory (void)
         rsvd_region[n].end   = (unsigned long) ia64_imva(_end);
         n++;
 
+        n += paravirt_reserve_memory(&rsvd_region[n]);
+
 #ifdef CONFIG_BLK_DEV_INITRD
         if (ia64_boot_param->initrd_start) {
                 rsvd_region[n].start = (unsigned long)__va(ia64_boot_param->initrd_start);
@@ -519,6 +522,8 @@ setup_arch (char **cmdline_p)
 {
         unw_init();
 
+        paravirt_arch_setup_early();
+
         ia64_patch_vtop((u64) __start___vtop_patchlist, (u64) __end___vtop_patchlist);
 
         *cmdline_p = __va(ia64_boot_param->command_line);
@@ -583,6 +588,9 @@ setup_arch (char **cmdline_p)
         acpi_boot_init();
 #endif
 
+        paravirt_banner();
+        paravirt_arch_setup_console(cmdline_p);
+
 #ifdef CONFIG_VT
         if (!conswitchp) {
 # if defined(CONFIG_DUMMY_CONSOLE)
@@ -602,6 +610,8 @@ setup_arch (char **cmdline_p)
 #endif
 
         /* enable IA-64 Machine Check Abort Handling unless disabled */
+        if (paravirt_arch_setup_nomca())
+                nomca = 1;
         if (!nomca)
                 ia64_mca_init();
 
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 9d1d429c6c59..03f1a9908afc 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -50,6 +50,7 @@
 #include <asm/machvec.h>
 #include <asm/mca.h>
 #include <asm/page.h>
+#include <asm/paravirt.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -642,6 +643,7 @@ void __devinit smp_prepare_boot_cpu(void)
         cpu_set(smp_processor_id(), cpu_online_map);
         cpu_set(smp_processor_id(), cpu_callin_map);
         per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+        paravirt_post_smp_prepare_boot_cpu();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index aad1b7b1fff9..65c10a42c88f 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -24,6 +24,7 @@
 #include <asm/machvec.h>
 #include <asm/delay.h>
 #include <asm/hw_irq.h>
+#include <asm/paravirt.h>
 #include <asm/ptrace.h>
 #include <asm/sal.h>
 #include <asm/sections.h>
@@ -48,6 +49,15 @@ EXPORT_SYMBOL(last_cli_ip);
 
 #endif
 
+#ifdef CONFIG_PARAVIRT
+static void
+paravirt_clocksource_resume(void)
+{
+        if (pv_time_ops.clocksource_resume)
+                pv_time_ops.clocksource_resume();
+}
+#endif
+
 static struct clocksource clocksource_itc = {
         .name           = "itc",
         .rating         = 350,
@@ -56,6 +66,9 @@ static struct clocksource clocksource_itc = {
         .mult           = 0, /*to be calculated*/
         .shift          = 16,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+#ifdef CONFIG_PARAVIRT
+        .resume         = paravirt_clocksource_resume,
+#endif
 };
 static struct clocksource *itc_clocksource;
 
@@ -157,6 +170,9 @@ timer_interrupt (int irq, void *dev_id)
 
         profile_tick(CPU_PROFILING);
 
+        if (paravirt_do_steal_accounting(&new_itm))
+                goto skip_process_time_accounting;
+
         while (1) {
                 update_process_times(user_mode(get_irq_regs()));
 
@@ -186,6 +202,8 @@ timer_interrupt (int irq, void *dev_id)
                 local_irq_disable();
         }
 
+skip_process_time_accounting:
+
         do {
                 /*
                  * If we're too close to the next clock tick for
@@ -335,6 +353,11 @@ ia64_init_itm (void)
                  */
                 clocksource_itc.rating = 50;
 
+        paravirt_init_missing_ticks_accounting(smp_processor_id());
+
+        /* avoid softlock up message when cpu is unplug and plugged again. */
+        touch_softlockup_watchdog();
+
         /* Setup the CPU local timer tick */
         ia64_cpu_local_tick();
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 5929ab10a289..5a77206c2492 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -4,7 +4,6 @@
 #include <asm/system.h>
 #include <asm/pgtable.h>
 
-#define LOAD_OFFSET     (KERNEL_START - KERNEL_TR_PAGE_SIZE)
 #include <asm-generic/vmlinux.lds.h>
 
 #define IVT_TEXT                                                        \