[PATCH 12/17] PVH xen: support invalid op, return PVH features etc...

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

The biggest change in this patch is in traps.c to allow forced invalid
op for PVH guest. Also, enable hypercall page init for PVH guest also.
Finally, set guest type to PVH if PV with HAP is created.

Changes in V2:
  - Fix emulate_forced_invalid_op() to use proper copy function, and inject PF
    in case it fails.
  - remove extraneous PVH check in STI/CLI ops en emulate_privileged_op().
  - Make assert a debug ASSERT in show_registers().
  - debug.c: keep get_gfn() locked and move put_gfn closer to it.

Changes in V3:
  - Mostly formatting.

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
---
 xen/arch/x86/debug.c        |    7 +++----
 xen/arch/x86/traps.c        |   25 ++++++++++++++++++++++++-
 xen/arch/x86/x86_64/traps.c |    7 ++++---
 xen/common/domain.c         |    9 +++++++++
 xen/common/domctl.c         |    5 +++++
 xen/common/kernel.c         |    6 +++++-
 6 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/xen/arch/x86/debug.c b/xen/arch/x86/debug.c
index 167421d..235f0bb 100644
--- a/xen/arch/x86/debug.c
+++ b/xen/arch/x86/debug.c
@@ -59,7 +59,9 @@ dbg_hvm_va2mfn(dbgva_t vaddr, struct domain *dp, int toaddr,
         return INVALID_MFN;
     }
 
-    mfn = mfn_x(get_gfn(dp, *gfn, &gfntype)); 
+    mfn = mfn_x(get_gfn_query(dp, *gfn, &gfntype));
+    put_gfn(dp, *gfn);
+
     if ( p2m_is_readonly(gfntype) && toaddr )
     {
         DBGP2("kdb:p2m_is_readonly: gfntype:%x\n", gfntype);
@@ -178,9 +180,6 @@ dbg_rw_guest_mem(dbgva_t addr, dbgbyte_t *buf, int len, struct domain *dp,
         }
 
         unmap_domain_page(va);
-        if ( gfn != INVALID_GFN )
-            put_gfn(dp, gfn);
-
         addr += pagecnt;
         buf += pagecnt;
         len -= pagecnt;
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index b95bed5..9e819b5 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -459,6 +459,10 @@ static void instruction_done(
     struct cpu_user_regs *regs, unsigned long eip, unsigned int bpmatch)
 {
     regs->eip = eip;
+
+    if ( is_pvh_vcpu(current) )
+        return;
+
     regs->eflags &= ~X86_EFLAGS_RF;
     if ( bpmatch || (regs->eflags & X86_EFLAGS_TF) )
     {
@@ -475,6 +479,9 @@ static unsigned int check_guest_io_breakpoint(struct vcpu *v,
     unsigned int width, i, match = 0;
     unsigned long start;
 
+    if ( is_pvh_vcpu(v) )
+        return 0;          /* PVH fixme: support io breakpoint */
+
     if ( !(v->arch.debugreg[5]) ||
          !(v->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE) )
         return 0;
@@ -1077,6 +1084,9 @@ void propagate_page_fault(unsigned long addr, u16 error_code)
     struct vcpu *v = current;
     struct trap_bounce *tb = &v->arch.pv_vcpu.trap_bounce;
 
+    /* PVH should not get here. (ctrlreg is not implemented) */
+    ASSERT(!is_pvh_vcpu(v));
+
     v->arch.pv_vcpu.ctrlreg[2] = addr;
     arch_set_cr2(v, addr);
 
@@ -1462,6 +1472,9 @@ static int read_descriptor(unsigned int sel,
 {
     struct desc_struct desc;
 
+    if ( is_pvh_vcpu(v) )
+        return hvm_read_descriptor(sel, v, regs, base, limit, ar);
+
     if ( !vm86_mode(regs) )
     {
         if ( sel < 4)
@@ -1580,6 +1593,13 @@ static int guest_io_okay(
     int user_mode = !(v->arch.flags & TF_kernel_mode);
 #define TOGGLE_MODE() if ( user_mode ) toggle_guest_mode(v)
 
+    /*
+     * For PVH we check this in vmexit for EXIT_REASON_IO_INSTRUCTION
+     * and so don't need to check again here.
+     */
+    if ( is_pvh_vcpu(v) )
+        return 1;
+
     if ( !vm86_mode(regs) &&
          (v->arch.pv_vcpu.iopl >= (guest_kernel_mode(v, regs) ? 1 : 3)) )
         return 1;
@@ -1825,7 +1845,7 @@ static inline uint64_t guest_misc_enable(uint64_t val)
         _ptr = (unsigned int)_ptr;                                          \
     if ( (limit) < sizeof(_x) - 1 || (eip) > (limit) - (sizeof(_x) - 1) )   \
         goto fail;                                                          \
-    if ( (_rc = copy_from_user(&_x, (type *)_ptr, sizeof(_x))) != 0 )       \
+    if ( (_rc = raw_copy_from_guest(&_x, (type *)_ptr, sizeof(_x))) != 0 )  \
     {                                                                       \
         propagate_page_fault(_ptr + sizeof(_x) - _rc, 0);                   \
         goto skip;                                                          \
@@ -3252,6 +3272,9 @@ void do_device_not_available(struct cpu_user_regs *regs)
 
     BUG_ON(!guest_mode(regs));
 
+    /* PVH should not get here. (ctrlreg is not implemented) */
+    ASSERT(!is_pvh_vcpu(curr));
+
     vcpu_restore_fpu_lazy(curr);
 
     if ( curr->arch.pv_vcpu.ctrlreg[0] & X86_CR0_TS )
diff --git a/xen/arch/x86/x86_64/traps.c b/xen/arch/x86/x86_64/traps.c
index d2f7209..a47b8d4 100644
--- a/xen/arch/x86/x86_64/traps.c
+++ b/xen/arch/x86/x86_64/traps.c
@@ -146,8 +146,8 @@ void vcpu_show_registers(const struct vcpu *v)
     const struct cpu_user_regs *regs = &v->arch.user_regs;
     unsigned long crs[8];
 
-    /* No need to handle HVM for now. */
-    if ( is_hvm_vcpu(v) )
+    /* No need to handle HVM and PVH for now. */
+    if ( !is_pv_vcpu(v) )
         return;
 
     crs[0] = v->arch.pv_vcpu.ctrlreg[0];
@@ -440,6 +440,7 @@ static long register_guest_callback(struct callback_register *reg)
     long ret = 0;
     struct vcpu *v = current;
 
+    ASSERT( !is_pvh_vcpu(v) );
     if ( !is_canonical_address(reg->address) )
         return -EINVAL;
 
@@ -620,7 +621,7 @@ static void hypercall_page_initialise_ring3_kernel(void *hypercall_page)
 void hypercall_page_initialise(struct domain *d, void *hypercall_page)
 {
     memset(hypercall_page, 0xCC, PAGE_SIZE);
-    if ( is_hvm_domain(d) )
+    if ( !is_pv_domain(d) )
         hvm_hypercall_page_initialise(d, hypercall_page);
     else if ( !is_pv_32bit_domain(d) )
         hypercall_page_initialise_ring3_kernel(hypercall_page);
diff --git a/xen/common/domain.c b/xen/common/domain.c
index 9b8368c..e1a2397 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -235,6 +235,15 @@ struct domain *domain_create(
 
     if ( domcr_flags & DOMCRF_hvm )
         d->guest_type = is_hvm;
+    else if ( domcr_flags & DOMCRF_pvh )
+    {
+        if ( !(domcr_flags & DOMCRF_hap) )
+        {
+            dprintk(XENLOG_ERR, "PVH guest must have HAP on\n");
+            goto fail;
+        }
+        d->guest_type = is_pvh;
+    }
 
     if ( domid == 0 )
     {
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index 6bd8efd..7dec348 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -186,6 +186,8 @@ void getdomaininfo(struct domain *d, struct xen_domctl_getdomaininfo *info)
 
     if ( is_hvm_domain(d) )
         info->flags |= XEN_DOMINF_hvm_guest;
+    else if ( is_pvh_domain(d) )
+        info->flags |= XEN_DOMINF_pvh_guest;
 
     xsm_security_domaininfo(d, info);
 
@@ -437,6 +439,9 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
         domcr_flags = 0;
         if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_hvm_guest )
             domcr_flags |= DOMCRF_hvm;
+        else if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_hap )
+            domcr_flags |= DOMCRF_pvh;     /* PV with HAP is a PVH guest */
+
         if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_hap )
             domcr_flags |= DOMCRF_hap;
         if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_s3_integrity )
diff --git a/xen/common/kernel.c b/xen/common/kernel.c
index 72fb905..3bba758 100644
--- a/xen/common/kernel.c
+++ b/xen/common/kernel.c
@@ -289,7 +289,11 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
             if ( current->domain == dom0 )
                 fi.submap |= 1U << XENFEAT_dom0;
 #ifdef CONFIG_X86
-            if ( !is_hvm_vcpu(current) )
+            if ( is_pvh_vcpu(current) )
+                fi.submap |= (1U << XENFEAT_hvm_safe_pvclock) |
+                             (1U << XENFEAT_supervisor_mode_kernel) |
+                             (1U << XENFEAT_hvm_callback_vector);
+            else if ( !is_hvm_vcpu(current) )
                 fi.submap |= (1U << XENFEAT_mmu_pt_update_preserve_ad) |
                              (1U << XENFEAT_highmem_assist) |
                              (1U << XENFEAT_gnttab_map_avail_bits);
-- 
1.7.2.3