x86/HVM: don't #GP/#SS on wrapping virt->linear translations

Real hardware wraps silently in most cases, so we should behave the
same. Also split real and VM86 mode handling, as the latter really
ought to have limit checks applied.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
v3: Restore 32-bit wrap check for AMD.
v2: Extend to non-64-bit modes. Reduce 64-bit check to a single
    is_canonical_address() invocation.

--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -2416,16 +2416,21 @@ bool_t hvm_virtual_to_linear_addr(
      */
     ASSERT(seg < x86_seg_none);
 
-    if ( !(curr->arch.hvm_vcpu.guest_cr[0] & X86_CR0_PE) ||
-         (guest_cpu_user_regs()->eflags & X86_EFLAGS_VM) )
+    if ( !(curr->arch.hvm_vcpu.guest_cr[0] & X86_CR0_PE) )
     {
         /*
-         * REAL/VM86 MODE: Don't bother with segment access checks.
+         * REAL MODE: Don't bother with segment access checks.
          * Certain of them are not done in native real mode anyway.
          */
         addr = (uint32_t)(addr + reg->base);
-        last_byte = (uint32_t)addr + bytes - !!bytes;
-        if ( last_byte < addr )
+    }
+    else if ( (guest_cpu_user_regs()->eflags & X86_EFLAGS_VM) &&
+              is_x86_user_segment(seg) )
+    {
+        /* VM86 MODE: Fixed 64k limits on all user segments. */
+        addr = (uint32_t)(addr + reg->base);
+        last_byte = (uint32_t)offset + bytes - !!bytes;
+        if ( max(offset, last_byte) >> 16 )
             goto out;
     }
     else if ( hvm_long_mode_active(curr) &&
@@ -2447,8 +2452,7 @@ bool_t hvm_virtual_to_linear_addr(
             addr += reg->base;
 
         last_byte = addr + bytes - !!bytes;
-        if ( !is_canonical_address(addr) || last_byte < addr ||
-             !is_canonical_address(last_byte) )
+        if ( !is_canonical_address((long)addr < 0 ? addr : last_byte) )
             goto out;
     }
     else
@@ -2498,8 +2502,11 @@ bool_t hvm_virtual_to_linear_addr(
             if ( (offset <= reg->limit) || (last_byte < offset) )
                 goto out;
         }
-        else if ( (last_byte > reg->limit) || (last_byte < offset) )
-            goto out; /* last byte is beyond limit or wraps 0xFFFFFFFF */
+        else if ( last_byte > reg->limit )
+            goto out; /* last byte is beyond limit */
+        else if ( last_byte < offset &&
+                  curr->domain->arch.cpuid->x86_vendor == X86_VENDOR_AMD )
+            goto out; /* access wraps */
     }
 
     /* All checks ok. */