References: bsc#995789 CVE-2016-7093 XSA-186

# Commit e9575f980df81aeb0e5b6139f485fd6f7bb7f5b6
# Date 2016-09-08 14:15:53 +0200
# Author Andrew Cooper <andrew.cooper3@citrix.com>
# Committer Jan Beulich <jbeulich@suse.com>
x86/emulate: Correct boundary interactions of emulated instructions

This reverts most of c/s 0640ffb6 "x86emul: fix rIP handling".

Experimentally, in long mode processors will execute an instruction stream
which crosses the 64bit -1 -> 0 virtual boundary, whether the instruction
boundary is aligned on the virtual boundary, or is misaligned.

In compatibility mode, Intel processors will execute an instruction stream
which crosses the 32bit -1 -> 0 virtual boundary, while AMD processors raise a
segmentation fault.  Xen's segmentation behaviour matches AMD.

For 16bit code, hardware does not ever truncated %ip.  %eip is always used and
behaves normally as a 32bit register, including in 16bit protected mode
segments, as well as in Real and Unreal mode.

This is XSA-186 / CVE-2016-7093.

Reported-by: Brian Marcotte <marcotte@panix.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -1538,10 +1538,6 @@ x86_emulate(
 #endif
     }
 
-    /* Truncate rIP to def_ad_bytes (2 or 4) if necessary. */
-    if ( def_ad_bytes < sizeof(_regs.eip) )
-        _regs.eip &= (1UL << (def_ad_bytes * 8)) - 1;
-
     /* Prefix bytes. */
     for ( ; ; )
     {
@@ -3843,21 +3839,11 @@ x86_emulate(
 
     /* Commit shadow register state. */
     _regs.eflags &= ~EFLG_RF;
-    switch ( __builtin_expect(def_ad_bytes, sizeof(_regs.eip)) )
-    {
-        uint16_t ip;
 
-    case 2:
-        ip = _regs.eip;
-        _regs.eip = ctxt->regs->eip;
-        *(uint16_t *)&_regs.eip = ip;
-        break;
-#ifdef __x86_64__
-    case 4:
-        _regs.rip = _regs._eip;
-        break;
-#endif
-    }
+    /* Zero the upper 32 bits of %rip if not in long mode. */
+    if ( def_ad_bytes < sizeof(_regs.eip) )
+        _regs.eip = (uint32_t)_regs.eip;
+
     *ctxt->regs = _regs;
 
  done: