diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index da1bf1a97b..8589d856be 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1511,6 +1511,9 @@ void paravirt_ctxt_switch_to(struct vcpu *v)
 {
     unsigned long cr4;
 
+    this_cpu(root_pgt)[root_table_offset(PERDOMAIN_VIRT_START)] =
+        l4e_from_page(v->domain->arch.perdomain_l3_pg, __PAGE_HYPERVISOR_RW);
+
     cr4 = pv_guest_cr4_to_real_cr4(v);
     if ( unlikely(cr4 != read_cr4()) )
         write_cr4(cr4);
@@ -1682,6 +1685,8 @@ void context_switch(struct vcpu *prev, struct vcpu *next)
 
     ASSERT(local_irq_is_enabled());
 
+    get_cpu_info()->xen_cr3 = 0;
+
     cpumask_copy(&dirty_mask, next->vcpu_dirty_cpumask);
     /* Allow at most one CPU at a time to be dirty. */
     ASSERT(cpumask_weight(&dirty_mask) <= 1);
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index a56f875d45..febc47369f 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -3520,6 +3520,7 @@ long do_mmu_update(
     struct vcpu *curr = current, *v = curr;
     struct domain *d = v->domain, *pt_owner = d, *pg_owner;
     mfn_t map_mfn = INVALID_MFN;
+    bool sync_guest = false;
     uint32_t xsm_needed = 0;
     uint32_t xsm_checked = 0;
     int rc = put_old_guest_table(curr);
@@ -3683,6 +3684,8 @@ long do_mmu_update(
                         break;
                     rc = mod_l4_entry(va, l4e_from_intpte(req.val), mfn,
                                       cmd == MMU_PT_UPDATE_PRESERVE_AD, v);
+                    if ( !rc )
+                        sync_guest = true;
                     break;
 
                 case PGT_writable_page:
@@ -3787,6 +3790,24 @@ long do_mmu_update(
     if ( va )
         unmap_domain_page(va);
 
+    if ( sync_guest )
+    {
+        /*
+         * Force other vCPU-s of the affected guest to pick up L4 entry
+         * changes (if any). Issue a flush IPI with empty operation mask to
+         * facilitate this (including ourselves waiting for the IPI to
+         * actually have arrived). Utilize the fact that FLUSH_VA_VALID is
+         * meaningless without FLUSH_CACHE, but will allow to pass the no-op
+         * check in flush_area_mask().
+         */
+        unsigned int cpu = smp_processor_id();
+        cpumask_t *mask = per_cpu(scratch_cpumask, cpu);
+
+        cpumask_andnot(mask, pt_owner->domain_dirty_cpumask, cpumask_of(cpu));
+        if ( !cpumask_empty(mask) )
+            flush_area_mask(mask, ZERO_BLOCK_PTR, FLUSH_VA_VALID);
+    }
+
     perfc_add(num_page_updates, i);
 
  out:
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 7b97ff86cb..69ac0d7c1e 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -327,6 +327,9 @@ void start_secondary(void *unused)
      */
     spin_debug_disable();
 
+    get_cpu_info()->xen_cr3 = 0;
+    get_cpu_info()->pv_cr3 = __pa(this_cpu(root_pgt));
+
     load_system_tables();
 
     /* Full exception support from here on in. */
@@ -633,6 +636,187 @@ void cpu_exit_clear(unsigned int cpu)
     set_cpu_state(CPU_STATE_DEAD);
 }
 
+static int clone_mapping(const void *ptr, root_pgentry_t *rpt)
+{
+    unsigned long linear = (unsigned long)ptr, pfn;
+    unsigned int flags;
+    l3_pgentry_t *pl3e = l4e_to_l3e(idle_pg_table[root_table_offset(linear)]) +
+                         l3_table_offset(linear);
+    l2_pgentry_t *pl2e;
+    l1_pgentry_t *pl1e;
+
+    if ( linear < DIRECTMAP_VIRT_START )
+        return 0;
+
+    flags = l3e_get_flags(*pl3e);
+    ASSERT(flags & _PAGE_PRESENT);
+    if ( flags & _PAGE_PSE )
+    {
+        pfn = (l3e_get_pfn(*pl3e) & ~((1UL << (2 * PAGETABLE_ORDER)) - 1)) |
+              (PFN_DOWN(linear) & ((1UL << (2 * PAGETABLE_ORDER)) - 1));
+        flags &= ~_PAGE_PSE;
+    }
+    else
+    {
+        pl2e = l3e_to_l2e(*pl3e) + l2_table_offset(linear);
+        flags = l2e_get_flags(*pl2e);
+        ASSERT(flags & _PAGE_PRESENT);
+        if ( flags & _PAGE_PSE )
+        {
+            pfn = (l2e_get_pfn(*pl2e) & ~((1UL << PAGETABLE_ORDER) - 1)) |
+                  (PFN_DOWN(linear) & ((1UL << PAGETABLE_ORDER) - 1));
+            flags &= ~_PAGE_PSE;
+        }
+        else
+        {
+            pl1e = l2e_to_l1e(*pl2e) + l1_table_offset(linear);
+            flags = l1e_get_flags(*pl1e);
+            if ( !(flags & _PAGE_PRESENT) )
+                return 0;
+            pfn = l1e_get_pfn(*pl1e);
+        }
+    }
+
+    if ( !(root_get_flags(rpt[root_table_offset(linear)]) & _PAGE_PRESENT) )
+    {
+        pl3e = alloc_xen_pagetable();
+        if ( !pl3e )
+            return -ENOMEM;
+        clear_page(pl3e);
+        l4e_write(&rpt[root_table_offset(linear)],
+                  l4e_from_paddr(__pa(pl3e), __PAGE_HYPERVISOR));
+    }
+    else
+        pl3e = l4e_to_l3e(rpt[root_table_offset(linear)]);
+
+    pl3e += l3_table_offset(linear);
+
+    if ( !(l3e_get_flags(*pl3e) & _PAGE_PRESENT) )
+    {
+        pl2e = alloc_xen_pagetable();
+        if ( !pl2e )
+            return -ENOMEM;
+        clear_page(pl2e);
+        l3e_write(pl3e, l3e_from_paddr(__pa(pl2e), __PAGE_HYPERVISOR));
+    }
+    else
+    {
+        ASSERT(!(l3e_get_flags(*pl3e) & _PAGE_PSE));
+        pl2e = l3e_to_l2e(*pl3e);
+    }
+
+    pl2e += l2_table_offset(linear);
+
+    if ( !(l2e_get_flags(*pl2e) & _PAGE_PRESENT) )
+    {
+        pl1e = alloc_xen_pagetable();
+        if ( !pl1e )
+            return -ENOMEM;
+        clear_page(pl1e);
+        l2e_write(pl2e, l2e_from_paddr(__pa(pl1e), __PAGE_HYPERVISOR));
+    }
+    else
+    {
+        ASSERT(!(l2e_get_flags(*pl2e) & _PAGE_PSE));
+        pl1e = l2e_to_l1e(*pl2e);
+    }
+
+    pl1e += l1_table_offset(linear);
+
+    if ( l1e_get_flags(*pl1e) & _PAGE_PRESENT )
+    {
+        ASSERT(l1e_get_pfn(*pl1e) == pfn);
+        ASSERT(l1e_get_flags(*pl1e) == flags);
+    }
+    else
+        l1e_write(pl1e, l1e_from_pfn(pfn, flags));
+
+    return 0;
+}
+
+DEFINE_PER_CPU(root_pgentry_t *, root_pgt);
+
+static int setup_cpu_root_pgt(unsigned int cpu)
+{
+    root_pgentry_t *rpt = alloc_xen_pagetable();
+    unsigned int off;
+    int rc;
+
+    if ( !rpt )
+        return -ENOMEM;
+
+    clear_page(rpt);
+    per_cpu(root_pgt, cpu) = rpt;
+
+    rpt[root_table_offset(RO_MPT_VIRT_START)] =
+        idle_pg_table[root_table_offset(RO_MPT_VIRT_START)];
+    /* SH_LINEAR_PT inserted together with guest mappings. */
+    /* PERDOMAIN inserted during context switch. */
+    rpt[root_table_offset(XEN_VIRT_START)] =
+        idle_pg_table[root_table_offset(XEN_VIRT_START)];
+
+    /* Install direct map page table entries for stack, IDT, and TSS. */
+    for ( off = rc = 0; !rc && off < STACK_SIZE; off += PAGE_SIZE )
+        rc = clone_mapping(__va(__pa(stack_base[cpu])) + off, rpt);
+
+    if ( !rc )
+        rc = clone_mapping(idt_tables[cpu], rpt);
+    if ( !rc )
+        rc = clone_mapping(&per_cpu(init_tss, cpu), rpt);
+
+    return rc;
+}
+
+static void cleanup_cpu_root_pgt(unsigned int cpu)
+{
+    root_pgentry_t *rpt = per_cpu(root_pgt, cpu);
+    unsigned int r;
+
+    if ( !rpt )
+        return;
+
+    per_cpu(root_pgt, cpu) = NULL;
+
+    for ( r = root_table_offset(DIRECTMAP_VIRT_START);
+          r < root_table_offset(HYPERVISOR_VIRT_END); ++r )
+    {
+        l3_pgentry_t *l3t;
+        unsigned int i3;
+
+        if ( !(root_get_flags(rpt[r]) & _PAGE_PRESENT) )
+            continue;
+
+        l3t = l4e_to_l3e(rpt[r]);
+
+        for ( i3 = 0; i3 < L3_PAGETABLE_ENTRIES; ++i3 )
+        {
+            l2_pgentry_t *l2t;
+            unsigned int i2;
+
+            if ( !(l3e_get_flags(l3t[i3]) & _PAGE_PRESENT) )
+                continue;
+
+            ASSERT(!(l3e_get_flags(l3t[i3]) & _PAGE_PSE));
+            l2t = l3e_to_l2e(l3t[i3]);
+
+            for ( i2 = 0; i2 < L2_PAGETABLE_ENTRIES; ++i2 )
+            {
+                if ( !(l2e_get_flags(l2t[i2]) & _PAGE_PRESENT) )
+                    continue;
+
+                ASSERT(!(l2e_get_flags(l2t[i2]) & _PAGE_PSE));
+                free_xen_pagetable(l2e_to_l1e(l2t[i2]));
+            }
+
+            free_xen_pagetable(l2t);
+        }
+
+        free_xen_pagetable(l3t);
+    }
+
+    free_xen_pagetable(rpt);
+}
+
 static void cpu_smpboot_free(unsigned int cpu)
 {
     unsigned int order, socket = cpu_to_socket(cpu);
@@ -671,6 +855,8 @@ static void cpu_smpboot_free(unsigned int cpu)
             free_domheap_page(mfn_to_page(mfn));
     }
 
+    cleanup_cpu_root_pgt(cpu);
+
     order = get_order_from_pages(NR_RESERVED_GDT_PAGES);
     free_xenheap_pages(per_cpu(gdt_table, cpu), order);
 
@@ -727,6 +913,11 @@ static int cpu_smpboot_alloc(unsigned int cpu)
     set_ist(&idt_tables[cpu][TRAP_nmi],           IST_NONE);
     set_ist(&idt_tables[cpu][TRAP_machine_check], IST_NONE);
 
+    rc = setup_cpu_root_pgt(cpu);
+    if ( rc )
+        goto out;
+    rc = -ENOMEM;
+
     for ( stub_page = 0, i = cpu & ~(STUBS_PER_PAGE - 1);
           i < nr_cpu_ids && i <= (cpu | (STUBS_PER_PAGE - 1)); ++i )
         if ( cpu_online(i) && cpu_to_node(i) == node )
@@ -786,6 +977,8 @@ static struct notifier_block cpu_smpboot_nfb = {
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
+    int rc;
+
     register_cpu_notifier(&cpu_smpboot_nfb);
 
     mtrr_aps_sync_begin();
@@ -799,6 +992,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
     stack_base[0] = stack_start;
 
+    rc = setup_cpu_root_pgt(0);
+    if ( rc )
+        panic("Error %d setting up PV root page table\n", rc);
+    get_cpu_info()->pv_cr3 = __pa(per_cpu(root_pgt, 0));
+
     set_nr_sockets();
 
     socket_cpumask = xzalloc_array(cpumask_t *, nr_sockets);
@@ -867,6 +1065,8 @@ void __init smp_prepare_boot_cpu(void)
 #if NR_CPUS > 2 * BITS_PER_LONG
     per_cpu(scratch_cpumask, cpu) = &scratch_cpu0mask;
 #endif
+
+    get_cpu_info()->xen_cr3 = 0;
 }
 
 static void
diff --git a/xen/arch/x86/x86_64/asm-offsets.c b/xen/arch/x86/x86_64/asm-offsets.c
index e136af6b99..b1a4310974 100644
--- a/xen/arch/x86/x86_64/asm-offsets.c
+++ b/xen/arch/x86/x86_64/asm-offsets.c
@@ -137,6 +137,8 @@ void __dummy__(void)
     OFFSET(CPUINFO_processor_id, struct cpu_info, processor_id);
     OFFSET(CPUINFO_current_vcpu, struct cpu_info, current_vcpu);
     OFFSET(CPUINFO_cr4, struct cpu_info, cr4);
+    OFFSET(CPUINFO_xen_cr3, struct cpu_info, xen_cr3);
+    OFFSET(CPUINFO_pv_cr3, struct cpu_info, pv_cr3);
     DEFINE(CPUINFO_sizeof, sizeof(struct cpu_info));
     BLANK();
 
diff --git a/xen/arch/x86/x86_64/compat/entry.S b/xen/arch/x86/x86_64/compat/entry.S
index 3fea54ee9d..e668f00c36 100644
--- a/xen/arch/x86/x86_64/compat/entry.S
+++ b/xen/arch/x86/x86_64/compat/entry.S
@@ -199,6 +199,17 @@ ENTRY(cstar_enter)
         pushq $0
         movl  $TRAP_syscall, 4(%rsp)
         SAVE_ALL
+
+        GET_STACK_END(bx)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rbx), %rcx
+        neg   %rcx
+        jz    .Lcstar_cr3_okay
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+        neg   %rcx
+        write_cr3 rcx, rdi, rsi
+        movq  $0, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+.Lcstar_cr3_okay:
+
         GET_CURRENT(bx)
         movq  VCPU_domain(%rbx),%rcx
         cmpb  $0,DOMAIN_is_32bit_pv(%rcx)
diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
index 1dd9ccf6a2..fc38874b1f 100644
--- a/xen/arch/x86/x86_64/entry.S
+++ b/xen/arch/x86/x86_64/entry.S
@@ -37,6 +37,32 @@ ENTRY(switch_to_kernel)
 /* %rbx: struct vcpu, interrupts disabled */
 restore_all_guest:
         ASSERT_INTERRUPTS_DISABLED
+
+        /* Copy guest mappings and switch to per-CPU root page table. */
+        mov   %cr3, %r9
+        GET_STACK_END(dx)
+        mov   STACK_CPUINFO_FIELD(pv_cr3)(%rdx), %rdi
+        movabs $PADDR_MASK & PAGE_MASK, %rsi
+        movabs $DIRECTMAP_VIRT_START, %rcx
+        mov   %rdi, %rax
+        and   %rsi, %rdi
+        and   %r9, %rsi
+        add   %rcx, %rdi
+        add   %rcx, %rsi
+        mov   $ROOT_PAGETABLE_FIRST_XEN_SLOT, %ecx
+        mov   root_table_offset(SH_LINEAR_PT_VIRT_START)*8(%rsi), %r8
+        mov   %r8, root_table_offset(SH_LINEAR_PT_VIRT_START)*8(%rdi)
+        rep movsq
+        mov   $ROOT_PAGETABLE_ENTRIES - \
+               ROOT_PAGETABLE_LAST_XEN_SLOT - 1, %ecx
+        sub   $(ROOT_PAGETABLE_FIRST_XEN_SLOT - \
+                ROOT_PAGETABLE_LAST_XEN_SLOT - 1) * 8, %rsi
+        sub   $(ROOT_PAGETABLE_FIRST_XEN_SLOT - \
+                ROOT_PAGETABLE_LAST_XEN_SLOT - 1) * 8, %rdi
+        rep movsq
+        mov   %r9, STACK_CPUINFO_FIELD(xen_cr3)(%rdx)
+        write_cr3 rax, rdi, rsi
+
         RESTORE_ALL
         testw $TRAP_syscall,4(%rsp)
         jz    iret_exit_to_guest
@@ -71,6 +97,22 @@ iret_exit_to_guest:
         ALIGN
 /* No special register assumptions. */
 restore_all_xen:
+        /*
+         * Check whether we need to switch to the per-CPU page tables, in
+         * case we return to late PV exit code (from an NMI or #MC).
+         */
+        GET_STACK_END(ax)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rax), %rdx
+        mov   STACK_CPUINFO_FIELD(pv_cr3)(%rax), %rax
+        test  %rdx, %rdx
+        /*
+         * Ideally the condition would be "nsz", but such doesn't exist,
+         * so "g" will have to do.
+         */
+UNLIKELY_START(g, exit_cr3)
+        write_cr3 rax, rdi, rsi
+UNLIKELY_END(exit_cr3)
+
         RESTORE_ALL adj=8
         iretq
 
@@ -100,7 +142,18 @@ ENTRY(lstar_enter)
         pushq $0
         movl  $TRAP_syscall, 4(%rsp)
         SAVE_ALL
-        GET_CURRENT(bx)
+
+        GET_STACK_END(bx)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rbx), %rcx
+        neg   %rcx
+        jz    .Llstar_cr3_okay
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+        neg   %rcx
+        write_cr3 rcx, rdi, rsi
+        movq  $0, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+.Llstar_cr3_okay:
+
+        __GET_CURRENT(bx)
         testb $TF_kernel_mode,VCPU_thread_flags(%rbx)
         jz    switch_to_kernel
 
@@ -192,7 +245,18 @@ GLOBAL(sysenter_eflags_saved)
         pushq $0
         movl  $TRAP_syscall, 4(%rsp)
         SAVE_ALL
-        GET_CURRENT(bx)
+
+        GET_STACK_END(bx)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rbx), %rcx
+        neg   %rcx
+        jz    .Lsyse_cr3_okay
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+        neg   %rcx
+        write_cr3 rcx, rdi, rsi
+        movq  $0, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+.Lsyse_cr3_okay:
+
+        __GET_CURRENT(bx)
         cmpb  $0,VCPU_sysenter_disables_events(%rbx)
         movq  VCPU_sysenter_addr(%rbx),%rax
         setne %cl
@@ -228,13 +292,23 @@ ENTRY(int80_direct_trap)
         movl  $0x80, 4(%rsp)
         SAVE_ALL
 
+        GET_STACK_END(bx)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rbx), %rcx
+        neg   %rcx
+        jz    .Lint80_cr3_okay
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+        neg   %rcx
+        write_cr3 rcx, rdi, rsi
+        movq  $0, STACK_CPUINFO_FIELD(xen_cr3)(%rbx)
+.Lint80_cr3_okay:
+
         cmpb  $0,untrusted_msi(%rip)
 UNLIKELY_START(ne, msi_check)
         movl  $0x80,%edi
         call  check_for_unexpected_msi
 UNLIKELY_END(msi_check)
 
-        GET_CURRENT(bx)
+        __GET_CURRENT(bx)
 
         /* Check that the callback is non-null. */
         leaq  VCPU_int80_bounce(%rbx),%rdx
@@ -391,9 +465,27 @@ ENTRY(dom_crash_sync_extable)
 
 ENTRY(common_interrupt)
         SAVE_ALL CLAC
+
+        GET_STACK_END(14)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%r14), %rcx
+        mov   %rcx, %r15
+        neg   %rcx
+        jz    .Lintr_cr3_okay
+        jns   .Lintr_cr3_load
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+        neg   %rcx
+.Lintr_cr3_load:
+        write_cr3 rcx, rdi, rsi
+        xor   %ecx, %ecx
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+        testb $3, UREGS_cs(%rsp)
+        cmovnz %rcx, %r15
+.Lintr_cr3_okay:
+
         CR4_PV32_RESTORE
         movq %rsp,%rdi
         callq do_IRQ
+        mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
         jmp ret_from_intr
 
 /* No special register assumptions. */
@@ -411,6 +503,23 @@ ENTRY(page_fault)
 /* No special register assumptions. */
 GLOBAL(handle_exception)
         SAVE_ALL CLAC
+
+        GET_STACK_END(14)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%r14), %rcx
+        mov   %rcx, %r15
+        neg   %rcx
+        jz    .Lxcpt_cr3_okay
+        jns   .Lxcpt_cr3_load
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+        neg   %rcx
+.Lxcpt_cr3_load:
+        write_cr3 rcx, rdi, rsi
+        xor   %ecx, %ecx
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+        testb $3, UREGS_cs(%rsp)
+        cmovnz %rcx, %r15
+.Lxcpt_cr3_okay:
+
 handle_exception_saved:
         GET_CURRENT(bx)
         testb $X86_EFLAGS_IF>>8,UREGS_eflags+1(%rsp)
@@ -475,6 +584,7 @@ handle_exception_saved:
         leaq  exception_table(%rip),%rdx
         PERFC_INCR(exceptions, %rax, %rbx)
         callq *(%rdx,%rax,8)
+        mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
         testb $3,UREGS_cs(%rsp)
         jz    restore_all_xen
         leaq  VCPU_trap_bounce(%rbx),%rdx
@@ -507,6 +617,7 @@ exception_with_ints_disabled:
         rep;  movsq                     # make room for ec/ev
 1:      movq  UREGS_error_code(%rsp),%rax # ec/ev
         movq  %rax,UREGS_kernel_sizeof(%rsp)
+        mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
         jmp   restore_all_xen           # return to fixup code
 
 /* No special register assumptions. */
@@ -585,6 +696,17 @@ ENTRY(double_fault)
         movl  $TRAP_double_fault,4(%rsp)
         /* Set AC to reduce chance of further SMAP faults */
         SAVE_ALL STAC
+
+        GET_STACK_END(bx)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%rbx), %rbx
+        test  %rbx, %rbx
+        jz    .Ldblf_cr3_okay
+        jns   .Ldblf_cr3_load
+        neg   %rbx
+.Ldblf_cr3_load:
+        write_cr3 rbx, rdi, rsi
+.Ldblf_cr3_okay:
+
         movq  %rsp,%rdi
         call  do_double_fault
         BUG   /* do_double_fault() shouldn't return. */
@@ -603,10 +725,28 @@ ENTRY(nmi)
         movl  $TRAP_nmi,4(%rsp)
 handle_ist_exception:
         SAVE_ALL CLAC
+
+        GET_STACK_END(14)
+        mov   STACK_CPUINFO_FIELD(xen_cr3)(%r14), %rcx
+        mov   %rcx, %r15
+        neg   %rcx
+        jz    .List_cr3_okay
+        jns   .List_cr3_load
+        mov   %rcx, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+        neg   %rcx
+.List_cr3_load:
+        write_cr3 rcx, rdi, rsi
+        movq  $0, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
+.List_cr3_okay:
+
         CR4_PV32_RESTORE
         testb $3,UREGS_cs(%rsp)
         jz    1f
-        /* Interrupted guest context. Copy the context to stack bottom. */
+        /*
+         * Interrupted guest context. Clear the restore value for xen_cr3
+         * and copy the context to stack bottom.
+         */
+        xor   %r15, %r15
         GET_CPUINFO_FIELD(guest_cpu_user_regs,di)
         movq  %rsp,%rsi
         movl  $UREGS_kernel_sizeof/8,%ecx
@@ -616,6 +756,7 @@ handle_ist_exception:
         movzbl UREGS_entry_vector(%rsp),%eax
         leaq  exception_table(%rip),%rdx
         callq *(%rdx,%rax,8)
+        mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)
         cmpb  $TRAP_nmi,UREGS_entry_vector(%rsp)
         jne   ret_from_intr
 
diff --git a/xen/include/asm-x86/asm_defns.h b/xen/include/asm-x86/asm_defns.h
index 7e8838e49b..73d96227f4 100644
--- a/xen/include/asm-x86/asm_defns.h
+++ b/xen/include/asm-x86/asm_defns.h
@@ -93,9 +93,30 @@ void ret_from_intr(void);
         UNLIKELY_DONE(mp, tag);   \
         __UNLIKELY_END(tag)
 
+        .equ .Lrax, 0
+        .equ .Lrcx, 1
+        .equ .Lrdx, 2
+        .equ .Lrbx, 3
+        .equ .Lrsp, 4
+        .equ .Lrbp, 5
+        .equ .Lrsi, 6
+        .equ .Lrdi, 7
+        .equ .Lr8,  8
+        .equ .Lr9,  9
+        .equ .Lr10, 10
+        .equ .Lr11, 11
+        .equ .Lr12, 12
+        .equ .Lr13, 13
+        .equ .Lr14, 14
+        .equ .Lr15, 15
+
 #define STACK_CPUINFO_FIELD(field) (1 - CPUINFO_sizeof + CPUINFO_##field)
 #define GET_STACK_END(reg)                        \
+        .if .Lr##reg > 8;                         \
+        movq $STACK_SIZE-1, %r##reg;              \
+        .else;                                    \
         movl $STACK_SIZE-1, %e##reg;              \
+        .endif;                                   \
         orq  %rsp, %r##reg
 
 #define GET_CPUINFO_FIELD(field, reg)             \
@@ -177,6 +198,15 @@ void ret_from_intr(void);
 #define ASM_STAC ASM_AC(STAC)
 #define ASM_CLAC ASM_AC(CLAC)
 
+.macro write_cr3 val:req, tmp1:req, tmp2:req
+        mov   %cr4, %\tmp1
+        mov   %\tmp1, %\tmp2
+        and   $~X86_CR4_PGE, %\tmp1
+        mov   %\tmp1, %cr4
+        mov   %\val, %cr3
+        mov   %\tmp2, %cr4
+.endm
+
 #define CR4_PV32_RESTORE                                           \
         667: ASM_NOP5;                                             \
         .pushsection .altinstr_replacement, "ax";                  \
diff --git a/xen/include/asm-x86/current.h b/xen/include/asm-x86/current.h
index 89849929eb..b929c48c85 100644
--- a/xen/include/asm-x86/current.h
+++ b/xen/include/asm-x86/current.h
@@ -41,6 +41,18 @@ struct cpu_info {
     struct vcpu *current_vcpu;
     unsigned long per_cpu_offset;
     unsigned long cr4;
+    /*
+     * Of the two following fields the latter is being set to the CR3 value
+     * to be used on the given pCPU for loading whenever 64-bit PV guest
+     * context is being entered. The value never changes once set.
+     * The former is the value to restore when re-entering Xen, if any. IOW
+     * its value being zero means there's nothing to restore. However, its
+     * value can also be negative, indicating to the exit-to-Xen code that
+     * restoring is not necessary, but allowing any nested entry code paths
+     * to still know the value to put back into CR3.
+     */
+    unsigned long xen_cr3;
+    unsigned long pv_cr3;
     /* get_stack_bottom() must be 16-byte aligned */
 };
 
diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index 41a8d8c32f..2962e83464 100644
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -462,6 +462,7 @@ extern idt_entry_t idt_table[];
 extern idt_entry_t *idt_tables[];
 
 DECLARE_PER_CPU(struct tss_struct, init_tss);
+DECLARE_PER_CPU(root_pgentry_t *, root_pgt);
 
 extern void init_int80_direct_trap(struct vcpu *v);
 
diff --git a/xen/include/asm-x86/x86_64/page.h b/xen/include/asm-x86/x86_64/page.h
index 6fb7cd5553..05a0334893 100644
--- a/xen/include/asm-x86/x86_64/page.h
+++ b/xen/include/asm-x86/x86_64/page.h
@@ -24,8 +24,8 @@
 /* These are architectural limits. Current CPUs support only 40-bit phys. */
 #define PADDR_BITS              52
 #define VADDR_BITS              48
-#define PADDR_MASK              ((1UL << PADDR_BITS)-1)
-#define VADDR_MASK              ((1UL << VADDR_BITS)-1)
+#define PADDR_MASK              ((_AC(1,UL) << PADDR_BITS) - 1)
+#define VADDR_MASK              ((_AC(1,UL) << VADDR_BITS) - 1)
 
 #define VADDR_TOP_BIT           (1UL << (VADDR_BITS - 1))
 #define CANONICAL_MASK          (~0UL & ~VADDR_MASK)
@@ -107,6 +107,7 @@ typedef l4_pgentry_t root_pgentry_t;
       : (((_s) < ROOT_PAGETABLE_FIRST_XEN_SLOT) ||  \
          ((_s) > ROOT_PAGETABLE_LAST_XEN_SLOT)))
 
+#define root_table_offset         l4_table_offset
 #define root_get_pfn              l4e_get_pfn
 #define root_get_flags            l4e_get_flags
 #define root_get_intpte           l4e_get_intpte