[V11 PATCH 09/21] PVH xen: domain create, context switch related code changes

[Mukesh Rathor <mukesh.rathor@oracle.com>]

This patch mostly contains changes to arch/x86/domain.c to allow for a PVH
domain creation. The new function pvh_set_vcpu_info(), introduced in the
previous patch, is called here to set some guest context in the VMCS.
This patch also changes the context_switch code in the same file to follow
HVM behaviour for PVH.

Changes in V2:
  - changes to read_segment_register() moved to this patch.

Changes in V3:
  - Fix read_segment_register() macro to make sure args are evaluated once,
    and use # instead of STR for name in the macro.

Changes in V4:
  - Remove pvh substruct in the hvm substruct, as the vcpu_info_mfn has been
    moved out of pv_vcpu struct.
  - rename hvm_pvh_* functions to hvm_*.

Changes in V5:
  - remove pvh_read_descriptor().

Changes in V7:
  - remove hap_update_cr3() and read_segment_register changes from here.

Changes in V11:
  - set cr3 to page_to_maddr and not page_to_mfn.
  - reject non-zero cr1 value for pvh.
  - Do not check for pvh in destroy_gdt, but put the check in callers.
  - Set _VPF_in_reset for PVH also.

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Tim Deegan <tim@xen.org>
PV-HVM-Regression-Tested-by: Andrew Cooper <andrew.cooper3@citrix.com>
---
 xen/arch/x86/domain.c |   65 +++++++++++++++++++++++++++++++++----------------
 1 files changed, 44 insertions(+), 21 deletions(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index d124507..917eb6a 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -385,7 +385,7 @@ int vcpu_initialise(struct vcpu *v)
 
     vmce_init_vcpu(v);
 
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
     {
         rc = hvm_vcpu_initialise(v);
         goto done;
@@ -452,7 +452,7 @@ void vcpu_destroy(struct vcpu *v)
 
     vcpu_destroy_fpu(v);
 
-    if ( is_hvm_vcpu(v) )
+    if ( !is_pv_vcpu(v) )
         hvm_vcpu_destroy(v);
     else
         xfree(v->arch.pv_vcpu.trap_ctxt);
@@ -464,7 +464,7 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
     int rc = -ENOMEM;
 
     d->arch.hvm_domain.hap_enabled =
-        is_hvm_domain(d) &&
+        !is_pv_domain(d) &&
         hvm_funcs.hap_supported &&
         (domcr_flags & DOMCRF_hap);
     d->arch.hvm_domain.mem_sharing_enabled = 0;
@@ -512,7 +512,7 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
     mapcache_domain_init(d);
 
     HYPERVISOR_COMPAT_VIRT_START(d) =
-        is_hvm_domain(d) ? ~0u : __HYPERVISOR_COMPAT_VIRT_START;
+        is_pv_domain(d) ? __HYPERVISOR_COMPAT_VIRT_START : ~0u;
 
     if ( (rc = paging_domain_init(d, domcr_flags)) != 0 )
         goto fail;
@@ -555,7 +555,7 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
     }
     spin_lock_init(&d->arch.e820_lock);
 
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
     {
         if ( (rc = hvm_domain_initialise(d)) != 0 )
         {
@@ -650,7 +650,7 @@ int arch_set_info_guest(
 #define c(fld) (compat ? (c.cmp->fld) : (c.nat->fld))
     flags = c(flags);
 
-    if ( !is_hvm_vcpu(v) )
+    if ( is_pv_vcpu(v) )
     {
         if ( !compat )
         {
@@ -703,7 +703,7 @@ int arch_set_info_guest(
     v->fpu_initialised = !!(flags & VGCF_I387_VALID);
 
     v->arch.flags &= ~TF_kernel_mode;
-    if ( (flags & VGCF_in_kernel) || is_hvm_vcpu(v)/*???*/ )
+    if ( (flags & VGCF_in_kernel) || !is_pv_vcpu(v)/*???*/ )
         v->arch.flags |= TF_kernel_mode;
 
     v->arch.vgc_flags = flags;
@@ -718,7 +718,7 @@ int arch_set_info_guest(
     if ( !compat )
     {
         memcpy(&v->arch.user_regs, &c.nat->user_regs, sizeof(c.nat->user_regs));
-        if ( !is_hvm_vcpu(v) )
+        if ( is_pv_vcpu(v) )
             memcpy(v->arch.pv_vcpu.trap_ctxt, c.nat->trap_ctxt,
                    sizeof(c.nat->trap_ctxt));
     }
@@ -734,10 +734,13 @@ int arch_set_info_guest(
 
     v->arch.user_regs.eflags |= 2;
 
-    if ( is_hvm_vcpu(v) )
+    if ( !is_pv_vcpu(v) )
     {
         hvm_set_info_guest(v);
-        goto out;
+        if ( is_hvm_vcpu(v) || v->is_initialised )
+            goto out;
+        else
+            goto pvh_skip_pv_stuff;
     }
 
     init_int80_direct_trap(v);
@@ -850,6 +853,7 @@ int arch_set_info_guest(
     if ( rc != 0 )
         return rc;
 
+ pvh_skip_pv_stuff:
     set_bit(_VPF_in_reset, &v->pause_flags);
 
     if ( !compat )
@@ -860,7 +864,7 @@ int arch_set_info_guest(
 
     if ( !cr3_page )
         rc = -EINVAL;
-    else if ( paging_mode_refcounts(d) )
+    else if ( paging_mode_refcounts(d) || is_pvh_vcpu(v) )
         /* nothing */;
     else if ( cr3_page == v->arch.old_guest_table )
     {
@@ -892,8 +896,19 @@ int arch_set_info_guest(
         /* handled below */;
     else if ( !compat )
     {
+        /* PVH 32bitfixme. */
+        if ( is_pvh_vcpu(v) )
+        {
+            v->arch.cr3 = page_to_maddr(cr3_page);
+            v->arch.hvm_vcpu.guest_cr[3] = c.nat->ctrlreg[3];
+        }
+
         v->arch.guest_table = pagetable_from_page(cr3_page);
-        if ( c.nat->ctrlreg[1] )
+
+        if ( c.nat->ctrlreg[1] && is_pvh_vcpu(v) )
+            rc = -EINVAL;
+
+        if ( c.nat->ctrlreg[1] && is_pv_vcpu(v) )
         {
             cr3_gfn = xen_cr3_to_pfn(c.nat->ctrlreg[1]);
             cr3_page = get_page_from_gfn(d, cr3_gfn, NULL, P2M_ALLOC);
@@ -936,7 +951,8 @@ int arch_set_info_guest(
     {
         if ( cr3_page )
             put_page(cr3_page);
-        destroy_gdt(v);
+        if ( !is_pvh_vcpu(v) )
+            destroy_gdt(v);
         return rc;
     }
 
@@ -953,6 +969,13 @@ int arch_set_info_guest(
 
     update_cr3(v);
 
+    if ( is_pvh_vcpu(v) )
+    {
+        /* Set VMCS fields. */
+        if ( (rc = pvh_vcpu_boot_set_info(v, c.nat)) != 0 )
+            return rc;
+    }
+
  out:
     if ( flags & VGCF_online )
         clear_bit(_VPF_down, &v->pause_flags);
@@ -964,7 +987,7 @@ int arch_set_info_guest(
 
 int arch_vcpu_reset(struct vcpu *v)
 {
-    if ( !is_hvm_vcpu(v) )
+    if ( is_pv_vcpu(v) )
     {
         destroy_gdt(v);
         return vcpu_destroy_pagetables(v);
@@ -1314,7 +1337,7 @@ static void update_runstate_area(struct vcpu *v)
 
 static inline int need_full_gdt(struct vcpu *v)
 {
-    return (!is_hvm_vcpu(v) && !is_idle_vcpu(v));
+    return (is_pv_vcpu(v) && !is_idle_vcpu(v));
 }
 
 static void __context_switch(void)
@@ -1449,7 +1472,7 @@ void context_switch(struct vcpu *prev, struct vcpu *next)
         /* Re-enable interrupts before restoring state which may fault. */
         local_irq_enable();
 
-        if ( !is_hvm_vcpu(next) )
+        if ( is_pv_vcpu(next) )
         {
             load_LDT(next);
             load_segments(next);
@@ -1575,12 +1598,12 @@ unsigned long hypercall_create_continuation(
         regs->eax  = op;
 
         /* Ensure the hypercall trap instruction is re-executed. */
-        if ( !is_hvm_vcpu(current) )
+        if ( is_pv_vcpu(current) )
             regs->eip -= 2;  /* re-execute 'syscall' / 'int $xx' */
         else
             current->arch.hvm_vcpu.hcall_preempted = 1;
 
-        if ( !is_hvm_vcpu(current) ?
+        if ( is_pv_vcpu(current) ?
              !is_pv_32on64_vcpu(current) :
              (hvm_guest_x86_mode(current) == 8) )
         {
@@ -1848,7 +1871,7 @@ int domain_relinquish_resources(struct domain *d)
                 return ret;
         }
 
-        if ( !is_hvm_domain(d) )
+        if ( is_pv_domain(d) )
         {
             for_each_vcpu ( d, v )
             {
@@ -1921,7 +1944,7 @@ int domain_relinquish_resources(struct domain *d)
         BUG();
     }
 
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
         hvm_domain_relinquish_resources(d);
 
     return 0;
@@ -2005,7 +2028,7 @@ void vcpu_mark_events_pending(struct vcpu *v)
     if ( already_pending )
         return;
 
-    if ( is_hvm_vcpu(v) )
+    if ( !is_pv_vcpu(v) )
         hvm_assert_evtchn_irq(v);
     else
         vcpu_kick(v);
-- 
1.7.2.3