[PATCH 17/18] PVH xen: HVM support of PVH guest creation/destruction

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

This patch implements the HVM/vmx portion of the guest create, ie
vcpu and domain initilization. Some changes to support the destroy path.

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
---
 xen/arch/x86/hvm/hvm.c     |   67 ++++++++++++++++++++++++++++++++++++++++++-
 xen/arch/x86/hvm/vmx/vmx.c |   40 ++++++++++++++++++++++++++
 2 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 3c1597b..2988a5f 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -510,6 +510,30 @@ static int hvm_print_line(
     return X86EMUL_OKAY;
 }
 
+static int pvh_dom_initialise(struct domain *d)
+{
+    int rc;
+
+    if ( !d->arch.hvm_domain.hap_enabled )
+        return -EINVAL;
+
+    spin_lock_init(&d->arch.hvm_domain.irq_lock);
+
+    hvm_init_cacheattr_region_list(d);
+
+    if ( (rc = paging_enable(d, PG_refcounts|PG_translate|PG_external)) != 0 )
+        goto pvh_dominit_fail;
+
+    if ( (rc = hvm_funcs.domain_initialise(d)) != 0 )
+        goto pvh_dominit_fail;
+
+    return 0;
+
+pvh_dominit_fail:
+    hvm_destroy_cacheattr_region_list(d);
+    return rc;
+}
+
 int hvm_domain_initialise(struct domain *d)
 {
     int rc;
@@ -520,6 +544,8 @@ int hvm_domain_initialise(struct domain *d)
                  "on a non-VT/AMDV platform.\n");
         return -EINVAL;
     }
+    if ( is_pvh_domain(d) )
+        return pvh_dom_initialise(d);
 
     spin_lock_init(&d->arch.hvm_domain.pbuf_lock);
     spin_lock_init(&d->arch.hvm_domain.irq_lock);
@@ -584,6 +610,9 @@ int hvm_domain_initialise(struct domain *d)
 
 void hvm_domain_relinquish_resources(struct domain *d)
 {
+    if ( is_pvh_domain(d) )
+        return;
+
     if ( hvm_funcs.nhvm_domain_relinquish_resources )
         hvm_funcs.nhvm_domain_relinquish_resources(d);
 
@@ -609,10 +638,14 @@ void hvm_domain_relinquish_resources(struct domain *d)
 void hvm_domain_destroy(struct domain *d)
 {
     hvm_funcs.domain_destroy(d);
+    hvm_destroy_cacheattr_region_list(d);
+
+    if ( is_pvh_domain(d) )
+        return;
+
     rtc_deinit(d);
     stdvga_deinit(d);
     vioapic_deinit(d);
-    hvm_destroy_cacheattr_region_list(d);
 }
 
 static int hvm_save_tsc_adjust(struct domain *d, hvm_domain_context_t *h)
@@ -1066,6 +1099,30 @@ static int __init __hvm_register_CPU_XSAVE_save_and_restore(void)
 }
 __initcall(__hvm_register_CPU_XSAVE_save_and_restore);
 
+static int pvh_vcpu_initialise(struct vcpu *v)
+{
+    int rc;
+
+    if ( (rc = hvm_funcs.vcpu_initialise(v)) != 0 )
+        return rc;
+
+    softirq_tasklet_init(&v->arch.hvm_vcpu.assert_evtchn_irq_tasklet,
+                         (void(*)(unsigned long))hvm_assert_evtchn_irq,
+                         (unsigned long)v);
+
+    v->arch.hvm_vcpu.hcall_64bit = 1;    /* PVH 32bitfixme. */
+    v->arch.user_regs.eflags = 2;
+    v->arch.hvm_vcpu.inject_trap.vector = -1;
+
+    if ( (rc = hvm_vcpu_cacheattr_init(v)) != 0 )
+    {
+        hvm_funcs.vcpu_destroy(v);
+        return rc;
+    }
+
+    return 0;
+}
+
 int hvm_vcpu_initialise(struct vcpu *v)
 {
     int rc;
@@ -1077,6 +1134,9 @@ int hvm_vcpu_initialise(struct vcpu *v)
     spin_lock_init(&v->arch.hvm_vcpu.tm_lock);
     INIT_LIST_HEAD(&v->arch.hvm_vcpu.tm_list);
 
+    if ( is_pvh_vcpu(v) )
+        return pvh_vcpu_initialise(v);
+
     if ( (rc = vlapic_init(v)) != 0 )
         goto fail1;
 
@@ -1165,7 +1225,10 @@ void hvm_vcpu_destroy(struct vcpu *v)
 
     tasklet_kill(&v->arch.hvm_vcpu.assert_evtchn_irq_tasklet);
     hvm_vcpu_cacheattr_destroy(v);
-    vlapic_destroy(v);
+
+    if ( !is_pvh_vcpu(v) )
+        vlapic_destroy(v);
+
     hvm_funcs.vcpu_destroy(v);
 
     /* Event channel is already freed by evtchn_destroy(). */
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 62cb84d..cb82523 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -82,6 +82,9 @@ static int vmx_domain_initialise(struct domain *d)
 {
     int rc;
 
+    if ( is_pvh_domain(d) )
+        return 0;
+
     if ( (rc = vmx_alloc_vlapic_mapping(d)) != 0 )
         return rc;
 
@@ -90,6 +93,9 @@ static int vmx_domain_initialise(struct domain *d)
 
 static void vmx_domain_destroy(struct domain *d)
 {
+    if ( is_pvh_domain(d) )
+        return;
+
     vmx_free_vlapic_mapping(d);
 }
 
@@ -113,6 +119,12 @@ static int vmx_vcpu_initialise(struct vcpu *v)
 
     vpmu_initialise(v);
 
+    if ( is_pvh_vcpu(v) )
+    {
+        /* This for hvm_long_mode_enabled(v). */
+        v->arch.hvm_vcpu.guest_efer = EFER_SCE | EFER_LMA | EFER_LME;
+        return 0;
+    }
     vmx_install_vlapic_mapping(v);
 
     /* %eax == 1 signals full real-mode support to the guest loader. */
@@ -1034,6 +1046,28 @@ static void vmx_update_host_cr3(struct vcpu *v)
     vmx_vmcs_exit(v);
 }
 
+/*
+ * PVH guest never causes CR3 write vmexit. This is called during the guest
+ * setup.
+ */
+static void vmx_update_pvh_cr(struct vcpu *v, unsigned int cr)
+{
+    vmx_vmcs_enter(v);
+    switch ( cr )
+    {
+    case 3:
+        __vmwrite(GUEST_CR3, v->arch.hvm_vcpu.guest_cr[3]);
+        hvm_asid_flush_vcpu(v);
+        break;
+
+    default:
+        printk(XENLOG_ERR
+               "PVH: d%d v%d unexpected cr%d update at rip:%lx\n",
+               v->domain->domain_id, v->vcpu_id, cr, __vmread(GUEST_RIP));
+    }
+    vmx_vmcs_exit(v);
+}
+
 void vmx_update_debug_state(struct vcpu *v)
 {
     unsigned long mask;
@@ -1053,6 +1087,12 @@ void vmx_update_debug_state(struct vcpu *v)
 
 static void vmx_update_guest_cr(struct vcpu *v, unsigned int cr)
 {
+    if ( is_pvh_vcpu(v) )
+    {
+        vmx_update_pvh_cr(v, cr);
+        return;
+    }
+
     vmx_vmcs_enter(v);
 
     switch ( cr )
-- 
1.7.2.3