KVM: ia64: Add interruption vector table for vmm

vmm_ivt.S includes an ivt for vmm use.

Signed-off-by: Anthony Xu <anthony.xu@intel.com>
Signed-off-by: Xiantao Zhang <xiantao.zhang@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

1 files changed, 1424 insertions, 0 deletions

diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S
new file mode 100644
index 00000000000..3ee5f481c06
--- /dev/null
+++ b/arch/ia64/kvm/vmm_ivt.S
@@ -0,0 +1,1424 @@
+/*
+ * /ia64/kvm_ivt.S
+ *
+ * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co
+ *      Stephane Eranian <eranian@hpl.hp.com>
+ *      David Mosberger <davidm@hpl.hp.com>
+ * Copyright (C) 2000, 2002-2003 Intel Co
+ *      Asit Mallick <asit.k.mallick@intel.com>
+ *      Suresh Siddha <suresh.b.siddha@intel.com>
+ *      Kenneth Chen <kenneth.w.chen@intel.com>
+ *      Fenghua Yu <fenghua.yu@intel.com>
+ *
+ *
+ * 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.
+ *
+ * 07/6/20 Xuefei Xu  (Anthony Xu) (anthony.xu@intel.com)
+ *              Supporting Intel virtualization architecture
+ *
+ */
+
+/*
+ * This file defines the interruption vector table used by the CPU.
+ * It does not include one entry per possible cause of interruption.
+ *
+ * The first 20 entries of the table contain 64 bundles each while the
+ * remaining 48 entries contain only 16 bundles each.
+ *
+ * The 64 bundles are used to allow inlining the whole handler for
+ * critical
+ * interruptions like TLB misses.
+ *
+ *  For each entry, the comment is as follows:
+ *
+ *              // 0x1c00 Entry 7 (size 64 bundles) Data Key Miss
+ *              (12,51)
+ *  entry offset ----/     /         /                  /
+ *  /
+ *  entry number ---------/         /                  /
+ *  /
+ *  size of the entry -------------/                  /
+ *  /
+ *  vector name -------------------------------------/
+ *  /
+ *  interruptions triggering this vector
+ *  ----------------------/
+ *
+ * The table is 32KB in size and must be aligned on 32KB
+ * boundary.
+ * (The CPU ignores the 15 lower bits of the address)
+ *
+ * Table is based upon EAS2.6 (Oct 1999)
+ */
+
+
+#include <asm/asmmacro.h>
+#include <asm/cache.h>
+#include <asm/pgtable.h>
+
+#include "asm-offsets.h"
+#include "vcpu.h"
+#include "kvm_minstate.h"
+#include "vti.h"
+
+#if 1
+# define PSR_DEFAULT_BITS   psr.ac
+#else
+# define PSR_DEFAULT_BITS   0
+#endif
+
+
+#define KVM_FAULT(n)    \
+    kvm_fault_##n:;          \
+    mov r19=n;;          \
+    br.sptk.many kvm_fault_##n;         \
+    ;;                  \
+
+
+#define KVM_REFLECT(n)    \
+    mov r31=pr;           \
+    mov r19=n;       /* prepare to save predicates */ \
+    mov r29=cr.ipsr;      \
+    ;;      \
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;       \
+(p7)br.sptk.many kvm_dispatch_reflection;        \
+    br.sptk.many kvm_panic;      \
+
+
+GLOBAL_ENTRY(kvm_panic)
+    br.sptk.many kvm_panic
+    ;;
+END(kvm_panic)
+
+
+
+
+
+    .section .text.ivt,"ax"
+
+    .align 32768    // align on 32KB boundary
+    .global kvm_ia64_ivt
+kvm_ia64_ivt:
+///////////////////////////////////////////////////////////////
+// 0x0000 Entry 0 (size 64 bundles) VHPT Translation (8,20,47)
+ENTRY(kvm_vhpt_miss)
+    KVM_FAULT(0)
+END(kvm_vhpt_miss)
+
+
+    .org kvm_ia64_ivt+0x400
+////////////////////////////////////////////////////////////////
+// 0x0400 Entry 1 (size 64 bundles) ITLB (21)
+ENTRY(kvm_itlb_miss)
+    mov r31 = pr
+    mov r29=cr.ipsr;
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+    (p6) br.sptk kvm_alt_itlb_miss
+    mov r19 = 1
+    br.sptk kvm_itlb_miss_dispatch
+    KVM_FAULT(1);
+END(kvm_itlb_miss)
+
+    .org kvm_ia64_ivt+0x0800
+//////////////////////////////////////////////////////////////////
+// 0x0800 Entry 2 (size 64 bundles) DTLB (9,48)
+ENTRY(kvm_dtlb_miss)
+    mov r31 = pr
+    mov r29=cr.ipsr;
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+(p6)br.sptk kvm_alt_dtlb_miss
+    br.sptk kvm_dtlb_miss_dispatch
+END(kvm_dtlb_miss)
+
+     .org kvm_ia64_ivt+0x0c00
+////////////////////////////////////////////////////////////////////
+// 0x0c00 Entry 3 (size 64 bundles) Alt ITLB (19)
+ENTRY(kvm_alt_itlb_miss)
+    mov r16=cr.ifa    // get address that caused the TLB miss
+    ;;
+    movl r17=PAGE_KERNEL
+    mov r24=cr.ipsr
+    movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+    ;;
+    and r19=r19,r16     // clear ed, reserved bits, and PTE control bits
+    ;;
+    or r19=r17,r19      // insert PTE control bits into r19
+    ;;
+    movl r20=IA64_GRANULE_SHIFT<<2
+    ;;
+    mov cr.itir=r20
+    ;;
+    itc.i r19		// insert the TLB entry
+    mov pr=r31,-1
+    rfi
+END(kvm_alt_itlb_miss)
+
+    .org kvm_ia64_ivt+0x1000
+/////////////////////////////////////////////////////////////////////
+// 0x1000 Entry 4 (size 64 bundles) Alt DTLB (7,46)
+ENTRY(kvm_alt_dtlb_miss)
+    mov r16=cr.ifa		// get address that caused the TLB miss
+    ;;
+    movl r17=PAGE_KERNEL
+    movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+    mov r24=cr.ipsr
+    ;;
+    and r19=r19,r16     // clear ed, reserved bits, and PTE control bits
+    ;;
+    or r19=r19,r17	// insert PTE control bits into r19
+    ;;
+    movl r20=IA64_GRANULE_SHIFT<<2
+    ;;
+    mov cr.itir=r20
+    ;;
+    itc.d r19		// insert the TLB entry
+    mov pr=r31,-1
+    rfi
+END(kvm_alt_dtlb_miss)
+
+    .org kvm_ia64_ivt+0x1400
+//////////////////////////////////////////////////////////////////////
+// 0x1400 Entry 5 (size 64 bundles) Data nested TLB (6,45)
+ENTRY(kvm_nested_dtlb_miss)
+    KVM_FAULT(5)
+END(kvm_nested_dtlb_miss)
+
+    .org kvm_ia64_ivt+0x1800
+/////////////////////////////////////////////////////////////////////
+// 0x1800 Entry 6 (size 64 bundles) Instruction Key Miss (24)
+ENTRY(kvm_ikey_miss)
+    KVM_REFLECT(6)
+END(kvm_ikey_miss)
+
+    .org kvm_ia64_ivt+0x1c00
+/////////////////////////////////////////////////////////////////////
+// 0x1c00 Entry 7 (size 64 bundles) Data Key Miss (12,51)
+ENTRY(kvm_dkey_miss)
+    KVM_REFLECT(7)
+END(kvm_dkey_miss)
+
+    .org kvm_ia64_ivt+0x2000
+////////////////////////////////////////////////////////////////////
+// 0x2000 Entry 8 (size 64 bundles) Dirty-bit (54)
+ENTRY(kvm_dirty_bit)
+    KVM_REFLECT(8)
+END(kvm_dirty_bit)
+
+    .org kvm_ia64_ivt+0x2400
+////////////////////////////////////////////////////////////////////
+// 0x2400 Entry 9 (size 64 bundles) Instruction Access-bit (27)
+ENTRY(kvm_iaccess_bit)
+    KVM_REFLECT(9)
+END(kvm_iaccess_bit)
+
+    .org kvm_ia64_ivt+0x2800
+///////////////////////////////////////////////////////////////////
+// 0x2800 Entry 10 (size 64 bundles) Data Access-bit (15,55)
+ENTRY(kvm_daccess_bit)
+    KVM_REFLECT(10)
+END(kvm_daccess_bit)
+
+    .org kvm_ia64_ivt+0x2c00
+/////////////////////////////////////////////////////////////////
+// 0x2c00 Entry 11 (size 64 bundles) Break instruction (33)
+ENTRY(kvm_break_fault)
+    mov r31=pr
+    mov r19=11
+    mov r29=cr.ipsr
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    ;;
+    alloc r14=ar.pfs,0,0,4,0 // now it's safe (must be first in insn group!)
+    mov out0=cr.ifa
+    mov out2=cr.isr     // FIXME: pity to make this slow access twice
+    mov out3=cr.iim     // FIXME: pity to make this slow access twice
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15)ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out1=16,sp
+    br.call.sptk.many b6=kvm_ia64_handle_break
+    ;;
+END(kvm_break_fault)
+
+    .org kvm_ia64_ivt+0x3000
+/////////////////////////////////////////////////////////////////
+// 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
+ENTRY(kvm_interrupt)
+    mov r31=pr		// prepare to save predicates
+    mov r19=12
+    mov r29=cr.ipsr
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT
+    tbit.z p0,p15=r29,IA64_PSR_I_BIT
+    ;;
+(p7) br.sptk kvm_dispatch_interrupt
+    ;;
+    mov r27=ar.rsc		/* M */
+    mov r20=r1			/* A */
+    mov r25=ar.unat		/* M */
+    mov r26=ar.pfs		/* I */
+    mov r28=cr.iip		/* M */
+    cover			/* B (or nothing) */
+    ;;
+    mov r1=sp
+    ;;
+    invala			/* M */
+    mov r30=cr.ifs
+    ;;
+    addl r1=-VMM_PT_REGS_SIZE,r1
+    ;;
+    adds r17=2*L1_CACHE_BYTES,r1	/* really: biggest cache-line size */
+    adds r16=PT(CR_IPSR),r1
+    ;;
+    lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES
+    st8 [r16]=r29			/* save cr.ipsr */
+    ;;
+    lfetch.fault.excl.nt1 [r17]
+    mov r29=b0
+    ;;
+    adds r16=PT(R8),r1  	/* initialize first base pointer */
+    adds r17=PT(R9),r1  	/* initialize second base pointer */
+    mov r18=r0      		/* make sure r18 isn't NaT */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r8,16
+.mem.offset 8,0; st8.spill [r17]=r9,16
+        ;;
+.mem.offset 0,0; st8.spill [r16]=r10,24
+.mem.offset 8,0; st8.spill [r17]=r11,24
+        ;;
+    st8 [r16]=r28,16		/* save cr.iip */
+    st8 [r17]=r30,16		/* save cr.ifs */
+    mov r8=ar.fpsr		/* M */
+    mov r9=ar.csd
+    mov r10=ar.ssd
+    movl r11=FPSR_DEFAULT	/* L-unit */
+    ;;
+    st8 [r16]=r25,16		/* save ar.unat */
+    st8 [r17]=r26,16		/* save ar.pfs */
+    shl r18=r18,16		/* compute ar.rsc to be used for "loadrs" */
+    ;;
+    st8 [r16]=r27,16		/* save ar.rsc */
+    adds r17=16,r17		/* skip over ar_rnat field */
+    ;;
+    st8 [r17]=r31,16		/* save predicates */
+    adds r16=16,r16		/* skip over ar_bspstore field */
+    ;;
+    st8 [r16]=r29,16		/* save b0 */
+    st8 [r17]=r18,16		/* save ar.rsc value for "loadrs" */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r20,16    /* save original r1 */
+.mem.offset 8,0; st8.spill [r17]=r12,16
+    adds r12=-16,r1
+    /* switch to kernel memory stack (with 16 bytes of scratch) */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r13,16
+.mem.offset 8,0; st8.spill [r17]=r8,16 /* save ar.fpsr */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r15,16
+.mem.offset 8,0; st8.spill [r17]=r14,16
+    dep r14=-1,r0,60,4
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r2,16
+.mem.offset 8,0; st8.spill [r17]=r3,16
+    adds r2=VMM_PT_REGS_R16_OFFSET,r1
+    adds r14 = VMM_VCPU_GP_OFFSET,r13
+    ;;
+    mov r8=ar.ccv
+    ld8 r14 = [r14]
+    ;;
+    mov r1=r14       /* establish kernel global pointer */
+    ;;                                          \
+    bsw.1
+    ;;
+    alloc r14=ar.pfs,0,0,1,0	// must be first in an insn group
+    mov out0=r13
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i
+    ;;
+    //(p15) ssm psr.i
+    adds r3=8,r2		// set up second base pointer for SAVE_REST
+    srlz.i			// ensure everybody knows psr.ic is back on
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r16,16
+.mem.offset 8,0; st8.spill [r3]=r17,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r18,16
+.mem.offset 8,0; st8.spill [r3]=r19,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r20,16
+.mem.offset 8,0; st8.spill [r3]=r21,16
+    mov r18=b6
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r22,16
+.mem.offset 8,0; st8.spill [r3]=r23,16
+    mov r19=b7
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r24,16
+.mem.offset 8,0; st8.spill [r3]=r25,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r26,16
+.mem.offset 8,0; st8.spill [r3]=r27,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r28,16
+.mem.offset 8,0; st8.spill [r3]=r29,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r30,16
+.mem.offset 8,0; st8.spill [r3]=r31,32
+    ;;
+    mov ar.fpsr=r11       /* M-unit */
+    st8 [r2]=r8,8         /* ar.ccv */
+    adds r24=PT(B6)-PT(F7),r3
+    ;;
+    stf.spill [r2]=f6,32
+    stf.spill [r3]=f7,32
+    ;;
+    stf.spill [r2]=f8,32
+    stf.spill [r3]=f9,32
+    ;;
+    stf.spill [r2]=f10
+    stf.spill [r3]=f11
+    adds r25=PT(B7)-PT(F11),r3
+    ;;
+    st8 [r24]=r18,16       /* b6 */
+    st8 [r25]=r19,16       /* b7 */
+    ;;
+    st8 [r24]=r9           /* ar.csd */
+    st8 [r25]=r10          /* ar.ssd */
+    ;;
+    srlz.d		// make sure we see the effect of cr.ivr
+    addl r14=@gprel(ia64_leave_nested),gp
+    ;;
+    mov rp=r14
+    br.call.sptk.many b6=kvm_ia64_handle_irq
+    ;;
+END(kvm_interrupt)
+
+    .global kvm_dispatch_vexirq
+    .org kvm_ia64_ivt+0x3400
+//////////////////////////////////////////////////////////////////////
+// 0x3400 Entry 13 (size 64 bundles) Reserved
+ENTRY(kvm_virtual_exirq)
+    mov r31=pr
+    mov r19=13
+    mov r30 =r0
+    ;;
+kvm_dispatch_vexirq:
+    cmp.eq p6,p0 = 1,r30
+    ;;
+(p6)add r29 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+(p6)ld8 r1 = [r29]
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,1,0
+    mov out0=r13
+
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    KVM_SAVE_REST
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    mov rp=r14
+    br.call.sptk.many b6=kvm_vexirq
+END(kvm_virtual_exirq)
+
+    .org kvm_ia64_ivt+0x3800
+/////////////////////////////////////////////////////////////////////
+// 0x3800 Entry 14 (size 64 bundles) Reserved
+    KVM_FAULT(14)
+    // this code segment is from 2.6.16.13
+
+
+    .org kvm_ia64_ivt+0x3c00
+///////////////////////////////////////////////////////////////////////
+// 0x3c00 Entry 15 (size 64 bundles) Reserved
+    KVM_FAULT(15)
+
+
+    .org kvm_ia64_ivt+0x4000
+///////////////////////////////////////////////////////////////////////
+// 0x4000 Entry 16 (size 64 bundles) Reserved
+    KVM_FAULT(16)
+
+    .org kvm_ia64_ivt+0x4400
+//////////////////////////////////////////////////////////////////////
+// 0x4400 Entry 17 (size 64 bundles) Reserved
+    KVM_FAULT(17)
+
+    .org kvm_ia64_ivt+0x4800
+//////////////////////////////////////////////////////////////////////
+// 0x4800 Entry 18 (size 64 bundles) Reserved
+    KVM_FAULT(18)
+
+    .org kvm_ia64_ivt+0x4c00
+//////////////////////////////////////////////////////////////////////
+// 0x4c00 Entry 19 (size 64 bundles) Reserved
+    KVM_FAULT(19)
+
+    .org kvm_ia64_ivt+0x5000
+//////////////////////////////////////////////////////////////////////
+// 0x5000 Entry 20 (size 16 bundles) Page Not Present
+ENTRY(kvm_page_not_present)
+    KVM_REFLECT(20)
+END(kvm_page_not_present)
+
+    .org kvm_ia64_ivt+0x5100
+///////////////////////////////////////////////////////////////////////
+// 0x5100 Entry 21 (size 16 bundles) Key Permission vector
+ENTRY(kvm_key_permission)
+    KVM_REFLECT(21)
+END(kvm_key_permission)
+
+    .org kvm_ia64_ivt+0x5200
+//////////////////////////////////////////////////////////////////////
+// 0x5200 Entry 22 (size 16 bundles) Instruction Access Rights (26)
+ENTRY(kvm_iaccess_rights)
+    KVM_REFLECT(22)
+END(kvm_iaccess_rights)
+
+    .org kvm_ia64_ivt+0x5300
+//////////////////////////////////////////////////////////////////////
+// 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53)
+ENTRY(kvm_daccess_rights)
+    KVM_REFLECT(23)
+END(kvm_daccess_rights)
+
+    .org kvm_ia64_ivt+0x5400
+/////////////////////////////////////////////////////////////////////
+// 0x5400 Entry 24 (size 16 bundles) General Exception (5,32,34,36,38,39)
+ENTRY(kvm_general_exception)
+   KVM_REFLECT(24)
+   KVM_FAULT(24)
+END(kvm_general_exception)
+
+    .org kvm_ia64_ivt+0x5500
+//////////////////////////////////////////////////////////////////////
+// 0x5500 Entry 25 (size 16 bundles) Disabled FP-Register (35)
+ENTRY(kvm_disabled_fp_reg)
+    KVM_REFLECT(25)
+END(kvm_disabled_fp_reg)
+
+    .org kvm_ia64_ivt+0x5600
+////////////////////////////////////////////////////////////////////
+// 0x5600 Entry 26 (size 16 bundles) Nat Consumption (11,23,37,50)
+ENTRY(kvm_nat_consumption)
+    KVM_REFLECT(26)
+END(kvm_nat_consumption)
+
+    .org kvm_ia64_ivt+0x5700
+/////////////////////////////////////////////////////////////////////
+// 0x5700 Entry 27 (size 16 bundles) Speculation (40)
+ENTRY(kvm_speculation_vector)
+    KVM_REFLECT(27)
+END(kvm_speculation_vector)
+
+    .org kvm_ia64_ivt+0x5800
+/////////////////////////////////////////////////////////////////////
+// 0x5800 Entry 28 (size 16 bundles) Reserved
+    KVM_FAULT(28)
+
+    .org kvm_ia64_ivt+0x5900
+///////////////////////////////////////////////////////////////////
+// 0x5900 Entry 29 (size 16 bundles) Debug (16,28,56)
+ENTRY(kvm_debug_vector)
+    KVM_FAULT(29)
+END(kvm_debug_vector)
+
+    .org kvm_ia64_ivt+0x5a00
+///////////////////////////////////////////////////////////////
+// 0x5a00 Entry 30 (size 16 bundles) Unaligned Reference (57)
+ENTRY(kvm_unaligned_access)
+    KVM_REFLECT(30)
+END(kvm_unaligned_access)
+
+    .org kvm_ia64_ivt+0x5b00
+//////////////////////////////////////////////////////////////////////
+// 0x5b00 Entry 31 (size 16 bundles) Unsupported Data Reference (57)
+ENTRY(kvm_unsupported_data_reference)
+    KVM_REFLECT(31)
+END(kvm_unsupported_data_reference)
+
+    .org kvm_ia64_ivt+0x5c00
+////////////////////////////////////////////////////////////////////
+// 0x5c00 Entry 32 (size 16 bundles) Floating Point FAULT (65)
+ENTRY(kvm_floating_point_fault)
+    KVM_REFLECT(32)
+END(kvm_floating_point_fault)
+
+    .org kvm_ia64_ivt+0x5d00
+/////////////////////////////////////////////////////////////////////
+// 0x5d00 Entry 33 (size 16 bundles) Floating Point Trap (66)
+ENTRY(kvm_floating_point_trap)
+    KVM_REFLECT(33)
+END(kvm_floating_point_trap)
+
+    .org kvm_ia64_ivt+0x5e00
+//////////////////////////////////////////////////////////////////////
+// 0x5e00 Entry 34 (size 16 bundles) Lower Privilege Transfer Trap (66)
+ENTRY(kvm_lower_privilege_trap)
+    KVM_REFLECT(34)
+END(kvm_lower_privilege_trap)
+
+    .org kvm_ia64_ivt+0x5f00
+//////////////////////////////////////////////////////////////////////
+// 0x5f00 Entry 35 (size 16 bundles) Taken Branch Trap (68)
+ENTRY(kvm_taken_branch_trap)
+    KVM_REFLECT(35)
+END(kvm_taken_branch_trap)
+
+    .org kvm_ia64_ivt+0x6000
+////////////////////////////////////////////////////////////////////
+// 0x6000 Entry 36 (size 16 bundles) Single Step Trap (69)
+ENTRY(kvm_single_step_trap)
+    KVM_REFLECT(36)
+END(kvm_single_step_trap)
+    .global kvm_virtualization_fault_back
+    .org kvm_ia64_ivt+0x6100
+/////////////////////////////////////////////////////////////////////
+// 0x6100 Entry 37 (size 16 bundles) Virtualization Fault
+ENTRY(kvm_virtualization_fault)
+    mov r31=pr
+    adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+    st8 [r16] = r1
+    adds r17 = VMM_VCPU_GP_OFFSET, r21
+    ;;
+    ld8 r1 = [r17]
+    cmp.eq p6,p0=EVENT_MOV_FROM_AR,r24
+    cmp.eq p7,p0=EVENT_MOV_FROM_RR,r24
+    cmp.eq p8,p0=EVENT_MOV_TO_RR,r24
+    cmp.eq p9,p0=EVENT_RSM,r24
+    cmp.eq p10,p0=EVENT_SSM,r24
+    cmp.eq p11,p0=EVENT_MOV_TO_PSR,r24
+    cmp.eq p12,p0=EVENT_THASH,r24
+    (p6) br.dptk.many kvm_asm_mov_from_ar
+    (p7) br.dptk.many kvm_asm_mov_from_rr
+    (p8) br.dptk.many kvm_asm_mov_to_rr
+    (p9) br.dptk.many kvm_asm_rsm
+    (p10) br.dptk.many kvm_asm_ssm
+    (p11) br.dptk.many kvm_asm_mov_to_psr
+    (p12) br.dptk.many kvm_asm_thash
+    ;;
+kvm_virtualization_fault_back:
+    adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+    ld8 r1 = [r16]
+    ;;
+    mov r19=37
+    adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+    adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+    ;;
+    st8 [r16] = r24
+    st8 [r17] = r25
+    ;;
+    cmp.ne p6,p0=EVENT_RFI, r24
+    (p6) br.sptk kvm_dispatch_virtualization_fault
+    ;;
+    adds r18=VMM_VPD_BASE_OFFSET,r21
+    ;;
+    ld8 r18=[r18]
+    ;;
+    adds r18=VMM_VPD_VIFS_OFFSET,r18
+    ;;
+    ld8 r18=[r18]
+    ;;
+    tbit.z p6,p0=r18,63
+    (p6) br.sptk kvm_dispatch_virtualization_fault
+    ;;
+    //if vifs.v=1 desert current register frame
+    alloc r18=ar.pfs,0,0,0,0
+    br.sptk kvm_dispatch_virtualization_fault
+END(kvm_virtualization_fault)
+
+    .org kvm_ia64_ivt+0x6200
+//////////////////////////////////////////////////////////////
+// 0x6200 Entry 38 (size 16 bundles) Reserved
+    KVM_FAULT(38)
+
+    .org kvm_ia64_ivt+0x6300
+/////////////////////////////////////////////////////////////////
+// 0x6300 Entry 39 (size 16 bundles) Reserved
+    KVM_FAULT(39)
+
+    .org kvm_ia64_ivt+0x6400
+/////////////////////////////////////////////////////////////////
+// 0x6400 Entry 40 (size 16 bundles) Reserved
+    KVM_FAULT(40)
+
+    .org kvm_ia64_ivt+0x6500
+//////////////////////////////////////////////////////////////////
+// 0x6500 Entry 41 (size 16 bundles) Reserved
+    KVM_FAULT(41)
+
+    .org kvm_ia64_ivt+0x6600
+//////////////////////////////////////////////////////////////////
+// 0x6600 Entry 42 (size 16 bundles) Reserved
+    KVM_FAULT(42)
+
+    .org kvm_ia64_ivt+0x6700
+//////////////////////////////////////////////////////////////////
+// 0x6700 Entry 43 (size 16 bundles) Reserved
+    KVM_FAULT(43)
+
+    .org kvm_ia64_ivt+0x6800
+//////////////////////////////////////////////////////////////////
+// 0x6800 Entry 44 (size 16 bundles) Reserved
+    KVM_FAULT(44)
+
+    .org kvm_ia64_ivt+0x6900
+///////////////////////////////////////////////////////////////////
+// 0x6900 Entry 45 (size 16 bundles) IA-32 Exeception
+//(17,18,29,41,42,43,44,58,60,61,62,72,73,75,76,77)
+ENTRY(kvm_ia32_exception)
+    KVM_FAULT(45)
+END(kvm_ia32_exception)
+
+    .org kvm_ia64_ivt+0x6a00
+////////////////////////////////////////////////////////////////////
+// 0x6a00 Entry 46 (size 16 bundles) IA-32 Intercept  (30,31,59,70,71)
+ENTRY(kvm_ia32_intercept)
+    KVM_FAULT(47)
+END(kvm_ia32_intercept)
+
+    .org kvm_ia64_ivt+0x6c00
+/////////////////////////////////////////////////////////////////////
+// 0x6c00 Entry 48 (size 16 bundles) Reserved
+    KVM_FAULT(48)
+
+    .org kvm_ia64_ivt+0x6d00
+//////////////////////////////////////////////////////////////////////
+// 0x6d00 Entry 49 (size 16 bundles) Reserved
+    KVM_FAULT(49)
+
+    .org kvm_ia64_ivt+0x6e00
+//////////////////////////////////////////////////////////////////////
+// 0x6e00 Entry 50 (size 16 bundles) Reserved
+    KVM_FAULT(50)
+
+    .org kvm_ia64_ivt+0x6f00
+/////////////////////////////////////////////////////////////////////
+// 0x6f00 Entry 51 (size 16 bundles) Reserved
+    KVM_FAULT(52)
+
+    .org kvm_ia64_ivt+0x7100
+////////////////////////////////////////////////////////////////////
+// 0x7100 Entry 53 (size 16 bundles) Reserved
+    KVM_FAULT(53)
+
+    .org kvm_ia64_ivt+0x7200
+/////////////////////////////////////////////////////////////////////
+// 0x7200 Entry 54 (size 16 bundles) Reserved
+    KVM_FAULT(54)
+
+    .org kvm_ia64_ivt+0x7300
+////////////////////////////////////////////////////////////////////
+// 0x7300 Entry 55 (size 16 bundles) Reserved
+    KVM_FAULT(55)
+
+    .org kvm_ia64_ivt+0x7400
+////////////////////////////////////////////////////////////////////
+// 0x7400 Entry 56 (size 16 bundles) Reserved
+    KVM_FAULT(56)
+
+    .org kvm_ia64_ivt+0x7500
+/////////////////////////////////////////////////////////////////////
+// 0x7500 Entry 57 (size 16 bundles) Reserved
+    KVM_FAULT(57)
+
+    .org kvm_ia64_ivt+0x7600
+/////////////////////////////////////////////////////////////////////
+// 0x7600 Entry 58 (size 16 bundles) Reserved
+    KVM_FAULT(58)
+
+    .org kvm_ia64_ivt+0x7700
+////////////////////////////////////////////////////////////////////
+// 0x7700 Entry 59 (size 16 bundles) Reserved
+    KVM_FAULT(59)
+
+    .org kvm_ia64_ivt+0x7800
+////////////////////////////////////////////////////////////////////
+// 0x7800 Entry 60 (size 16 bundles) Reserved
+    KVM_FAULT(60)
+
+    .org kvm_ia64_ivt+0x7900
+/////////////////////////////////////////////////////////////////////
+// 0x7900 Entry 61 (size 16 bundles) Reserved
+    KVM_FAULT(61)
+
+    .org kvm_ia64_ivt+0x7a00
+/////////////////////////////////////////////////////////////////////
+// 0x7a00 Entry 62 (size 16 bundles) Reserved
+    KVM_FAULT(62)
+
+    .org kvm_ia64_ivt+0x7b00
+/////////////////////////////////////////////////////////////////////
+// 0x7b00 Entry 63 (size 16 bundles) Reserved
+    KVM_FAULT(63)
+
+    .org kvm_ia64_ivt+0x7c00
+////////////////////////////////////////////////////////////////////
+// 0x7c00 Entry 64 (size 16 bundles) Reserved
+    KVM_FAULT(64)
+
+    .org kvm_ia64_ivt+0x7d00
+/////////////////////////////////////////////////////////////////////
+// 0x7d00 Entry 65 (size 16 bundles) Reserved
+    KVM_FAULT(65)
+
+    .org kvm_ia64_ivt+0x7e00
+/////////////////////////////////////////////////////////////////////
+// 0x7e00 Entry 66 (size 16 bundles) Reserved
+    KVM_FAULT(66)
+
+    .org kvm_ia64_ivt+0x7f00
+////////////////////////////////////////////////////////////////////
+// 0x7f00 Entry 67 (size 16 bundles) Reserved
+    KVM_FAULT(67)
+
+    .org kvm_ia64_ivt+0x8000
+// 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(kvm_dtlb_miss_dispatch)
+    mov r19 = 2
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,3,0
+    mov out0=cr.ifa
+    mov out1=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+    ;;
+    KVM_SAVE_REST
+    KVM_SAVE_EXTRA
+    mov rp=r14
+    ;;
+    adds out2=16,r12
+    br.call.sptk.many b6=kvm_page_fault
+END(kvm_dtlb_miss_dispatch)
+
+ENTRY(kvm_itlb_miss_dispatch)
+
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,3,0
+    mov out0=cr.ifa
+    mov out1=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out2=16,r12
+    br.call.sptk.many b6=kvm_page_fault
+END(kvm_itlb_miss_dispatch)
+
+ENTRY(kvm_dispatch_reflection)
+    /*
+     * Input:
+     *  psr.ic: off
+     *  r19:    intr type (offset into ivt, see ia64_int.h)
+     *  r31:    contains saved predicates (pr)
+     */
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,5,0
+    mov out0=cr.ifa
+    mov out1=cr.isr
+    mov out2=cr.iim
+    mov out3=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out4=16,r12
+    br.call.sptk.many b6=reflect_interruption
+END(kvm_dispatch_reflection)
+
+ENTRY(kvm_dispatch_virtualization_fault)
+    adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+    adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+    ;;
+    st8 [r16] = r24
+    st8 [r17] = r25
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    ;;
+    alloc r14=ar.pfs,0,0,2,0 // now it's safe (must be first in insn group!)
+    mov out0=r13        //vcpu
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+    ;;
+    KVM_SAVE_REST
+    KVM_SAVE_EXTRA
+    mov rp=r14
+    ;;
+    adds out1=16,sp         //regs
+    br.call.sptk.many b6=kvm_emulate
+END(kvm_dispatch_virtualization_fault)
+
+
+ENTRY(kvm_dispatch_interrupt)
+    KVM_SAVE_MIN_WITH_COVER_R19	// uses r31; defines r2 and r3
+    ;;
+    alloc r14=ar.pfs,0,0,1,0 // must be first in an insn group
+    //mov out0=cr.ivr		// pass cr.ivr as first arg
+    adds r3=8,r2		// set up second base pointer for SAVE_REST
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i
+    ;;
+    //(p15) ssm psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    mov out0=r13		// pass pointer to pt_regs as second arg
+    br.call.sptk.many b6=kvm_ia64_handle_irq
+END(kvm_dispatch_interrupt)
+
+
+
+
+GLOBAL_ENTRY(ia64_leave_nested)
+	rsm psr.i
+	;;
+	adds r21=PT(PR)+16,r12
+	;;
+	lfetch [r21],PT(CR_IPSR)-PT(PR)
+	adds r2=PT(B6)+16,r12
+	adds r3=PT(R16)+16,r12
+	;;
+	lfetch [r21]
+	ld8 r28=[r2],8		// load b6
+	adds r29=PT(R24)+16,r12
+
+	ld8.fill r16=[r3]
+	adds r3=PT(AR_CSD)-PT(R16),r3
+	adds r30=PT(AR_CCV)+16,r12
+	;;
+	ld8.fill r24=[r29]
+	ld8 r15=[r30]		// load ar.ccv
+	;;
+	ld8 r29=[r2],16		// load b7
+	ld8 r30=[r3],16		// load ar.csd
+	;;
+	ld8 r31=[r2],16		// load ar.ssd
+	ld8.fill r8=[r3],16
+	;;
+	ld8.fill r9=[r2],16
+	ld8.fill r10=[r3],PT(R17)-PT(R10)
+	;;
+	ld8.fill r11=[r2],PT(R18)-PT(R11)
+	ld8.fill r17=[r3],16
+	;;
+	ld8.fill r18=[r2],16
+	ld8.fill r19=[r3],16
+	;;
+	ld8.fill r20=[r2],16
+	ld8.fill r21=[r3],16
+	mov ar.csd=r30
+	mov ar.ssd=r31
+	;;
+	rsm psr.i | psr.ic
+	// initiate turning off of interrupt and interruption collection
+	invala			// invalidate ALAT
+	;;
+	srlz.i
+	;;
+	ld8.fill r22=[r2],24
+	ld8.fill r23=[r3],24
+	mov b6=r28
+	;;
+	ld8.fill r25=[r2],16
+	ld8.fill r26=[r3],16
+	mov b7=r29
+	;;
+	ld8.fill r27=[r2],16
+	ld8.fill r28=[r3],16
+	;;
+	ld8.fill r29=[r2],16
+	ld8.fill r30=[r3],24
+	;;
+	ld8.fill r31=[r2],PT(F9)-PT(R31)
+	adds r3=PT(F10)-PT(F6),r3
+	;;
+	ldf.fill f9=[r2],PT(F6)-PT(F9)
+	ldf.fill f10=[r3],PT(F8)-PT(F10)
+	;;
+	ldf.fill f6=[r2],PT(F7)-PT(F6)
+	;;
+	ldf.fill f7=[r2],PT(F11)-PT(F7)
+	ldf.fill f8=[r3],32
+	;;
+	srlz.i			// ensure interruption collection is off
+	mov ar.ccv=r15
+	;;
+	bsw.0	// switch back to bank 0 (no stop bit required beforehand...)
+	;;
+	ldf.fill f11=[r2]
+//	mov r18=r13
+//    mov r21=r13
+	adds r16=PT(CR_IPSR)+16,r12
+	adds r17=PT(CR_IIP)+16,r12
+	;;
+	ld8 r29=[r16],16	// load cr.ipsr
+	ld8 r28=[r17],16	// load cr.iip
+	;;
+	ld8 r30=[r16],16	// load cr.ifs
+	ld8 r25=[r17],16	// load ar.unat
+	;;
+	ld8 r26=[r16],16	// load ar.pfs
+	ld8 r27=[r17],16	// load ar.rsc
+	cmp.eq p9,p0=r0,r0
+	// set p9 to indicate that we should restore cr.ifs
+	;;
+	ld8 r24=[r16],16	// load ar.rnat (may be garbage)
+	ld8 r23=[r17],16// load ar.bspstore (may be garbage)
+	;;
+	ld8 r31=[r16],16	// load predicates
+	ld8 r22=[r17],16	// load b0
+	;;
+	ld8 r19=[r16],16	// load ar.rsc value for "loadrs"
+	ld8.fill r1=[r17],16	// load r1
+	;;
+	ld8.fill r12=[r16],16
+	ld8.fill r13=[r17],16
+	;;
+	ld8 r20=[r16],16	// ar.fpsr
+	ld8.fill r15=[r17],16
+	;;
+	ld8.fill r14=[r16],16
+	ld8.fill r2=[r17]
+	;;
+	ld8.fill r3=[r16]
+	;;
+	mov r16=ar.bsp		// get existing backing store pointer
+	;;
+	mov b0=r22
+	mov ar.pfs=r26
+	mov cr.ifs=r30
+	mov cr.ipsr=r29
+	mov ar.fpsr=r20
+	mov cr.iip=r28
+	;;
+	mov ar.rsc=r27
+	mov ar.unat=r25
+	mov pr=r31,-1
+	rfi
+END(ia64_leave_nested)
+
+
+
+GLOBAL_ENTRY(ia64_leave_hypervisor_prepare)
+    /*
+     * work.need_resched etc. mustn't get changed
+     *by this CPU before it returns to
+    ;;
+     * user- or fsys-mode, hence we disable interrupts early on:
+     */
+    adds r2 = PT(R4)+16,r12
+    adds r3 = PT(R5)+16,r12
+    adds r8 = PT(EML_UNAT)+16,r12
+    ;;
+    ld8 r8 = [r8]
+    ;;
+    mov ar.unat=r8
+    ;;
+    ld8.fill r4=[r2],16    //load r4
+    ld8.fill r5=[r3],16    //load r5
+    ;;
+    ld8.fill r6=[r2]    //load r6
+    ld8.fill r7=[r3]    //load r7
+    ;;
+END(ia64_leave_hypervisor_prepare)
+//fall through
+GLOBAL_ENTRY(ia64_leave_hypervisor)
+    rsm psr.i
+    ;;
+    br.call.sptk.many b0=leave_hypervisor_tail
+    ;;
+    adds r20=PT(PR)+16,r12
+    adds r8=PT(EML_UNAT)+16,r12
+    ;;
+    ld8 r8=[r8]
+    ;;
+    mov ar.unat=r8
+    ;;
+    lfetch [r20],PT(CR_IPSR)-PT(PR)
+    adds r2 = PT(B6)+16,r12
+    adds r3 = PT(B7)+16,r12
+    ;;
+    lfetch [r20]
+    ;;
+    ld8 r24=[r2],16        /* B6 */
+    ld8 r25=[r3],16        /* B7 */
+    ;;
+    ld8 r26=[r2],16        /* ar_csd */
+    ld8 r27=[r3],16        /* ar_ssd */
+    mov b6 = r24
+    ;;
+    ld8.fill r8=[r2],16
+    ld8.fill r9=[r3],16
+    mov b7 = r25
+    ;;
+    mov ar.csd = r26
+    mov ar.ssd = r27
+    ;;
+    ld8.fill r10=[r2],PT(R15)-PT(R10)
+    ld8.fill r11=[r3],PT(R14)-PT(R11)
+    ;;
+    ld8.fill r15=[r2],PT(R16)-PT(R15)
+    ld8.fill r14=[r3],PT(R17)-PT(R14)
+    ;;
+    ld8.fill r16=[r2],16
+    ld8.fill r17=[r3],16
+    ;;
+    ld8.fill r18=[r2],16
+    ld8.fill r19=[r3],16
+    ;;
+    ld8.fill r20=[r2],16
+    ld8.fill r21=[r3],16
+    ;;
+    ld8.fill r22=[r2],16
+    ld8.fill r23=[r3],16
+    ;;
+    ld8.fill r24=[r2],16
+    ld8.fill r25=[r3],16
+    ;;
+    ld8.fill r26=[r2],16
+    ld8.fill r27=[r3],16
+    ;;
+    ld8.fill r28=[r2],16
+    ld8.fill r29=[r3],16
+    ;;
+    ld8.fill r30=[r2],PT(F6)-PT(R30)
+    ld8.fill r31=[r3],PT(F7)-PT(R31)
+    ;;
+    rsm psr.i | psr.ic
+    // initiate turning off of interrupt and interruption collection
+    invala          // invalidate ALAT
+    ;;
+    srlz.i          // ensure interruption collection is off
+    ;;
+    bsw.0
+    ;;
+    adds r16 = PT(CR_IPSR)+16,r12
+    adds r17 = PT(CR_IIP)+16,r12
+    mov r21=r13		// get current
+    ;;
+    ld8 r31=[r16],16    // load cr.ipsr
+    ld8 r30=[r17],16    // load cr.iip
+    ;;
+    ld8 r29=[r16],16    // load cr.ifs
+    ld8 r28=[r17],16    // load ar.unat
+    ;;
+    ld8 r27=[r16],16    // load ar.pfs
+    ld8 r26=[r17],16    // load ar.rsc
+    ;;
+    ld8 r25=[r16],16    // load ar.rnat
+    ld8 r24=[r17],16    // load ar.bspstore
+    ;;
+    ld8 r23=[r16],16    // load predicates
+    ld8 r22=[r17],16    // load b0
+    ;;
+    ld8 r20=[r16],16    // load ar.rsc value for "loadrs"
+    ld8.fill r1=[r17],16    //load r1
+    ;;
+    ld8.fill r12=[r16],16    //load r12
+    ld8.fill r13=[r17],PT(R2)-PT(R13)    //load r13
+    ;;
+    ld8 r19=[r16],PT(R3)-PT(AR_FPSR)    //load ar_fpsr
+    ld8.fill r2=[r17],PT(AR_CCV)-PT(R2)    //load r2
+    ;;
+    ld8.fill r3=[r16]	//load r3
+    ld8 r18=[r17]	//load ar_ccv
+    ;;
+    mov ar.fpsr=r19
+    mov ar.ccv=r18
+    shr.u r18=r20,16
+    ;;
+kvm_rbs_switch:
+    mov r19=96
+
+kvm_dont_preserve_current_frame:
+/*
+    * To prevent leaking bits between the hypervisor and guest domain,
+    * we must clear the stacked registers in the "invalid" partition here.
+    * 5 registers/cycle on McKinley).
+    */
+#   define pRecurse	p6
+#   define pReturn	p7
+#   define Nregs	14
+
+    alloc loc0=ar.pfs,2,Nregs-2,2,0
+    shr.u loc1=r18,9		// RNaTslots <= floor(dirtySize / (64*8))
+    sub r19=r19,r18		// r19 = (physStackedSize + 8) - dirtySize
+    ;;
+    mov ar.rsc=r20		// load ar.rsc to be used for "loadrs"
+    shladd in0=loc1,3,r19
+    mov in1=0
+    ;;
+    TEXT_ALIGN(32)
+kvm_rse_clear_invalid:
+    alloc loc0=ar.pfs,2,Nregs-2,2,0
+    cmp.lt pRecurse,p0=Nregs*8,in0
+    // if more than Nregs regs left to clear, (re)curse
+    add out0=-Nregs*8,in0
+    add out1=1,in1		// increment recursion count
+    mov loc1=0
+    mov loc2=0
+    ;;
+    mov loc3=0
+    mov loc4=0
+    mov loc5=0
+    mov loc6=0
+    mov loc7=0
+(pRecurse) br.call.dptk.few b0=kvm_rse_clear_invalid
+    ;;
+    mov loc8=0
+    mov loc9=0
+    cmp.ne pReturn,p0=r0,in1
+    // if recursion count != 0, we need to do a br.ret
+    mov loc10=0
+    mov loc11=0
+(pReturn) br.ret.dptk.many b0
+
+#	undef pRecurse
+#	undef pReturn
+
+// loadrs has already been shifted
+    alloc r16=ar.pfs,0,0,0,0    // drop current register frame
+    ;;
+    loadrs
+    ;;
+    mov ar.bspstore=r24
+    ;;
+    mov ar.unat=r28
+    mov ar.rnat=r25
+    mov ar.rsc=r26
+    ;;
+    mov cr.ipsr=r31
+    mov cr.iip=r30
+    mov cr.ifs=r29
+    mov ar.pfs=r27
+    adds r18=VMM_VPD_BASE_OFFSET,r21
+    ;;
+    ld8 r18=[r18]   //vpd
+    adds r17=VMM_VCPU_ISR_OFFSET,r21
+    ;;
+    ld8 r17=[r17]
+    adds r19=VMM_VPD_VPSR_OFFSET,r18
+    ;;
+    ld8 r19=[r19]        //vpsr
+    adds r20=VMM_VCPU_VSA_BASE_OFFSET,r21
+    ;;
+    ld8 r20=[r20]
+    ;;
+//vsa_sync_write_start
+    mov r25=r18
+    adds r16= VMM_VCPU_GP_OFFSET,r21
+    ;;
+    ld8 r16= [r16] // Put gp in r24
+    movl r24=@gprel(ia64_vmm_entry)  // calculate return address
+    ;;
+    add  r24=r24,r16
+    ;;
+    add r16=PAL_VPS_SYNC_WRITE,r20
+    ;;
+    mov b0=r16
+    br.cond.sptk b0         // call the service
+    ;;
+END(ia64_leave_hypervisor)
+// fall through
+GLOBAL_ENTRY(ia64_vmm_entry)
+/*
+ *  must be at bank 0
+ *  parameter:
+ *  r17:cr.isr
+ *  r18:vpd
+ *  r19:vpsr
+ *  r20:__vsa_base
+ *  r22:b0
+ *  r23:predicate
+ */
+    mov r24=r22
+    mov r25=r18
+    tbit.nz p1,p2 = r19,IA64_PSR_IC_BIT        // p1=vpsr.ic
+    ;;
+    (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+    (p1) br.sptk.many ia64_vmm_entry_out
+    ;;
+    tbit.nz p1,p2 = r17,IA64_ISR_IR_BIT		//p1=cr.isr.ir
+    ;;
+    (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+    (p2) add r29=PAL_VPS_RESUME_HANDLER,r20
+    (p2) ld8 r26=[r25]
+    ;;
+ia64_vmm_entry_out:
+    mov pr=r23,-2
+    mov b0=r29
+    ;;
+    br.cond.sptk b0             // call pal service
+END(ia64_vmm_entry)
+
+
+
+/*
+ * extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2,
+ *                  u64 arg3, u64 arg4, u64 arg5,
+ *                  u64 arg6, u64 arg7);
+ *
+ * XXX: The currently defined services use only 4 args at the max. The
+ *  rest are not consumed.
+ */
+GLOBAL_ENTRY(ia64_call_vsa)
+    .regstk 4,4,0,0
+
+rpsave  =   loc0
+pfssave =   loc1
+psrsave =   loc2
+entry   =   loc3
+hostret =   r24
+
+    alloc   pfssave=ar.pfs,4,4,0,0
+    mov rpsave=rp
+    adds entry=VMM_VCPU_VSA_BASE_OFFSET, r13
+    ;;
+    ld8 entry=[entry]
+1:  mov hostret=ip
+    mov r25=in1         // copy arguments
+    mov r26=in2
+    mov r27=in3
+    mov psrsave=psr
+    ;;
+    tbit.nz p6,p0=psrsave,14    // IA64_PSR_I
+    tbit.nz p7,p0=psrsave,13    // IA64_PSR_IC
+    ;;
+    add hostret=2f-1b,hostret   // calculate return address
+    add entry=entry,in0
+    ;;
+    rsm psr.i | psr.ic
+    ;;
+    srlz.i
+    mov b6=entry
+    br.cond.sptk b6         // call the service
+2:
+    // Architectural sequence for enabling interrupts if necessary
+(p7)    ssm psr.ic
+    ;;
+(p7)    srlz.i
+    ;;
+//(p6)    ssm psr.i
+    ;;
+    mov rp=rpsave
+    mov ar.pfs=pfssave
+    mov r8=r31
+    ;;
+    srlz.d
+    br.ret.sptk rp
+
+END(ia64_call_vsa)
+
+#define  INIT_BSPSTORE  ((4<<30)-(12<<20)-0x100)
+
+GLOBAL_ENTRY(vmm_reset_entry)
+    //set up ipsr, iip, vpd.vpsr, dcr
+    // For IPSR: it/dt/rt=1, i/ic=1, si=1, vm/bn=1
+    // For DCR: all bits 0
+    adds r14=-VMM_PT_REGS_SIZE, r12
+    ;;
+    movl r6=0x501008826000      // IPSR dt/rt/it:1;i/ic:1, si:1, vm/bn:1
+    movl r10=0x8000000000000000
+    adds r16=PT(CR_IIP), r14
+    adds r20=PT(R1), r14
+    ;;
+    rsm psr.ic | psr.i
+    ;;
+    srlz.i
+    ;;
+    bsw.0
+    ;;
+    mov r21 =r13
+    ;;
+    bsw.1
+    ;;
+    mov ar.rsc = 0
+    ;;
+    flushrs
+    ;;
+    mov ar.bspstore = 0
+    // clear BSPSTORE
+    ;;
+    mov cr.ipsr=r6
+    mov cr.ifs=r10
+    ld8 r4 = [r16] // Set init iip for first run.
+    ld8 r1 = [r20]
+    ;;
+    mov cr.iip=r4
+    ;;
+    adds r16=VMM_VPD_BASE_OFFSET,r13
+    adds r20=VMM_VCPU_VSA_BASE_OFFSET,r13
+    ;;
+    ld8 r18=[r16]
+    ld8 r20=[r20]
+    ;;
+    adds r19=VMM_VPD_VPSR_OFFSET,r18
+    ;;
+    ld8 r19=[r19]
+    mov r17=r0
+    mov r22=r0
+    mov r23=r0
+    br.cond.sptk ia64_vmm_entry
+    br.ret.sptk  b0
+END(vmm_reset_entry)