[PATCH 08/17] PVH xen: domain creation code changes

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

This patch contains changes to arch/x86/domain.c to allow for a PVH
domain.
Changes in V2:
  - changes to read_segment_register() moved to this patch.
  - The other comment was to create NULL functions for pvh_set_vcpu_info
    and pvh_read_descriptor which are implemented in later patch, but since
    I disable PVH creation until all patches are checked in, it is not needed.
    But it helps breaking down of patches.

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_*.

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
---
 xen/arch/x86/domain.c         |   66 ++++++++++++++++++++++++++--------------
 xen/arch/x86/mm.c             |    3 ++
 xen/arch/x86/mm/hap/hap.c     |    4 ++-
 xen/include/asm-x86/hvm/hvm.h |   18 +++++++++++
 xen/include/asm-x86/system.h  |   18 +++++++++--
 5 files changed, 81 insertions(+), 28 deletions(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index b0fa339..b1fd758 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -389,7 +389,7 @@ int vcpu_initialise(struct vcpu *v)
 
     v->arch.vcpu_info_mfn = INVALID_MFN;
 
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
     {
         rc = hvm_vcpu_initialise(v);
         goto done;
@@ -456,7 +456,7 @@ 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);
@@ -468,7 +468,7 @@ 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;
@@ -516,7 +516,7 @@ 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;
@@ -558,7 +558,7 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
             goto fail;
     }
 
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
     {
         if ( (rc = hvm_domain_initialise(d)) != 0 )
         {
@@ -567,12 +567,11 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
         }
     }
     else
-    {
         /* 64-bit PV guest by default. */
         d->arch.is_32bit_pv = d->arch.has_32bit_shinfo = 0;
 
+    if ( !is_hvm_domain(d) )
         spin_lock_init(&d->arch.e820_lock);
-    }
 
     /* initialize default tsc behavior in case tools don't */
     tsc_set_info(d, TSC_MODE_DEFAULT, 0UL, 0, 0);
@@ -594,9 +593,10 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
 
 void arch_domain_destroy(struct domain *d)
 {
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
         hvm_domain_destroy(d);
-    else
+
+    if ( !is_hvm_domain(d) )
         xfree(d->arch.e820);
 
     free_domain_pirqs(d);
@@ -664,7 +664,7 @@ 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 )
         {
@@ -717,7 +717,7 @@ 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;
@@ -728,7 +728,7 @@ 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));
     }
@@ -744,10 +744,13 @@ 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);
@@ -756,7 +759,10 @@ int arch_set_info_guest(
     v->arch.pv_vcpu.iopl = (v->arch.user_regs.eflags >> 12) & 3;
     v->arch.user_regs.eflags &= ~X86_EFLAGS_IOPL;
 
-    /* Ensure real hardware interrupts are enabled. */
+    /*
+     * Ensure real hardware interrupts are enabled. Note: PVH may not have
+     * IDT set on all vcpus so we don't enable IF for it yet.
+     */
     v->arch.user_regs.eflags |= X86_EFLAGS_IF;
 
     if ( !v->is_initialised )
@@ -853,6 +859,7 @@ int arch_set_info_guest(
     if ( rc != 0 )
         return rc;
 
+pvh_skip_pv_stuff:
     if ( !compat )
     {
         cr3_gfn = xen_cr3_to_pfn(c.nat->ctrlreg[3]);
@@ -871,8 +878,14 @@ int arch_set_info_guest(
             return -EINVAL;
         }
 
+        if ( is_pvh_vcpu(v) )
+        {
+            v->arch.cr3 = page_to_mfn(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) )
         {
             cr3_gfn = xen_cr3_to_pfn(c.nat->ctrlreg[1]);
             cr3_page = get_page_from_gfn(d, cr3_gfn, NULL, P2M_ALLOC);
@@ -939,6 +952,13 @@ int arch_set_info_guest(
 
     update_cr3(v);
 
+    if ( is_pvh_vcpu(v) )
+    {
+        /* guest is bringing up non-boot SMP vcpu */
+        if ( (rc=hvm_set_vcpu_info(v, c.nat)) != 0 )
+            return rc;
+    }
+
  out:
     if ( flags & VGCF_online )
         clear_bit(_VPF_down, &v->pause_flags);
@@ -1444,7 +1464,7 @@ 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)
@@ -1578,7 +1598,7 @@ 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);
@@ -1701,12 +1721,12 @@ 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) )
         {
@@ -2022,7 +2042,7 @@ int domain_relinquish_resources(struct domain *d)
         for_each_vcpu ( d, v )
             vcpu_destroy_pagetables(v);
 
-        if ( !is_hvm_domain(d) )
+        if ( is_pv_domain(d) )
         {
             for_each_vcpu ( d, v )
             {
@@ -2097,7 +2117,7 @@ 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;
@@ -2181,7 +2201,7 @@ 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);
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 6a3d50a..d9bdded 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -4080,6 +4080,9 @@ void destroy_gdt(struct vcpu *v)
     int i;
     unsigned long pfn;
 
+    if ( is_pvh_vcpu(v) )
+        return;
+
     v->arch.pv_vcpu.gdt_ents = 0;
     pl1e = gdt_ldt_ptes(v->domain, v);
     for ( i = 0; i < FIRST_RESERVED_GDT_PAGE; i++ )
diff --git a/xen/arch/x86/mm/hap/hap.c b/xen/arch/x86/mm/hap/hap.c
index bff05d9..5aa0852 100644
--- a/xen/arch/x86/mm/hap/hap.c
+++ b/xen/arch/x86/mm/hap/hap.c
@@ -639,7 +639,9 @@ static void hap_update_cr3(struct vcpu *v, int do_locking)
 const struct paging_mode *
 hap_paging_get_mode(struct vcpu *v)
 {
-    return !hvm_paging_enabled(v)   ? &hap_paging_real_mode :
+    /* PVH 32bitfixme */
+    return is_pvh_vcpu(v) ? &hap_paging_long_mode :
+        !hvm_paging_enabled(v)   ? &hap_paging_real_mode :
         hvm_long_mode_enabled(v) ? &hap_paging_long_mode :
         hvm_pae_enabled(v)       ? &hap_paging_pae_mode  :
                                    &hap_paging_protected_mode;
diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
index 2fa2ea5..a790954 100644
--- a/xen/include/asm-x86/hvm/hvm.h
+++ b/xen/include/asm-x86/hvm/hvm.h
@@ -190,6 +190,11 @@ struct hvm_function_table {
                                 paddr_t *L1_gpa, unsigned int *page_order,
                                 uint8_t *p2m_acc, bool_t access_r,
                                 bool_t access_w, bool_t access_x);
+    /* PVH functions */
+    int (*pvh_set_vcpu_info)(struct vcpu *v, struct vcpu_guest_context *ctxtp);
+    int (*pvh_read_descriptor)(unsigned int sel, const struct vcpu *v,
+                         const struct cpu_user_regs *regs, unsigned long *base,
+                         unsigned long *limit, unsigned int *ar);
 };
 
 extern struct hvm_function_table hvm_funcs;
@@ -323,6 +328,19 @@ static inline unsigned long hvm_get_shadow_gs_base(struct vcpu *v)
     return hvm_funcs.get_shadow_gs_base(v);
 }
 
+static inline int hvm_set_vcpu_info(struct vcpu *v, 
+                                        struct vcpu_guest_context *ctxtp)
+{
+    return hvm_funcs.pvh_set_vcpu_info(v, ctxtp);
+}
+
+static inline int hvm_read_descriptor(unsigned int sel, 
+               const struct vcpu *v, const struct cpu_user_regs *regs, 
+               unsigned long *base, unsigned long *limit, unsigned int *ar)
+{
+    return hvm_funcs.pvh_read_descriptor(sel, v, regs, base, limit, ar);
+}
+
 #define is_viridian_domain(_d)                                             \
  (is_hvm_domain(_d) && ((_d)->arch.hvm_domain.params[HVM_PARAM_VIRIDIAN]))
 
diff --git a/xen/include/asm-x86/system.h b/xen/include/asm-x86/system.h
index d8dc6f2..7780c16 100644
--- a/xen/include/asm-x86/system.h
+++ b/xen/include/asm-x86/system.h
@@ -4,10 +4,20 @@
 #include <xen/lib.h>
 #include <asm/bitops.h>
 
-#define read_segment_register(vcpu, regs, name)                 \
-({  u16 __sel;                                                  \
-    asm volatile ( "movw %%" STR(name) ",%0" : "=r" (__sel) );  \
-    __sel;                                                      \
+/* 
+ * We need vcpu because during context switch, going from pure PV to PVH,
+ * in save_segments(), current has been updated to next, and no longer pointing
+ * to the pure PV. Note: for PVH, we update regs->selectors on each vmexit.
+ */
+#define read_segment_register(vcpu, regs, name)                   \
+({  u16 __sel;                                                    \
+    struct cpu_user_regs *_regs = (regs);                         \
+                                                                  \
+    if ( is_pvh_vcpu(vcpu) )                                      \
+        __sel = _regs->name;                                      \
+    else                                                          \
+        asm volatile ( "movw %%" #name ",%0" : "=r" (__sel) );    \
+    __sel;                                                        \
 })
 
 #define wbinvd() \
-- 
1.7.2.3