x86/emul: Correct the decoding of mov to/from cr/dr

The mov to/from cr/dr behave as if they were encoded with Mod = 3.  When
encoded with Mod != 3, no displacement or SIB bytes are fetched.

Add a test with a deliberately malformed ModRM byte.  (Also add the
automatically-generated simd.h to .gitignore.)

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: c2e316b2f2
master date: 2017-03-07 17:29:16 +0000

tools/tests/x86_emulator/test_x86_emulator.c

@@ -163,6 +163,18 @@ static inline uint64_t xgetbv(uint32_t xcr)
     (ebx & (1U << 5)) != 0; \
 })
 
+static int read_segment(
+    enum x86_segment seg,
+    struct segment_register *reg,
+    struct x86_emulate_ctxt *ctxt)
+{
+    if ( !is_x86_user_segment(seg) )
+        return X86EMUL_UNHANDLEABLE;
+    memset(reg, 0, sizeof(*reg));
+    reg->attr.fields.p = 1;
+    return X86EMUL_OKAY;
+}
+
 static int read_cr(
     unsigned int reg,
     unsigned long *val,
@@ -215,6 +227,7 @@ static struct x86_emulate_ops emulops = {
     .write      = write,
     .cmpxchg    = cmpxchg,
     .cpuid      = cpuid,
+    .read_segment = read_segment,
     .read_cr    = read_cr,
     .get_fpu    = get_fpu,
 };
@@ -732,6 +745,27 @@ int main(int argc, char **argv)
         goto fail;
     printf("okay\n");
 
+    printf("%-40s", "Testing mov %%cr4,%%esi (bad ModRM)...");
+    /*
+     * Mod = 1, Reg = 4, R/M = 6 would normally encode a memory reference of
+     * disp8(%esi), but mov to/from cr/dr are special and behave as if they
+     * were encoded with Mod == 3.
+     */
+    instr[0] = 0x0f; instr[1] = 0x20, instr[2] = 0x66;
+    instr[3] = 0; /* Supposed disp8. */
+    regs.esi = 0;
+    regs.eip = (unsigned long)&instr[0];
+    rc = x86_emulate(&ctxt, &emulops);
+    /*
+     * We don't care precicely what gets read from %cr4 into %esi, just so
+     * long as ModRM is treated as a register operand and 0(%esi) isn't
+     * followed as a memory reference.
+     */
+    if ( (rc != X86EMUL_OKAY) ||
+         (regs.eip != (unsigned long)&instr[3]) )
+        goto fail;
+    printf("okay\n");
+
 #define decl_insn(which) extern const unsigned char which[], which##_len[]
 #define put_insn(which, insn) ".pushsection .test, \"ax\", @progbits\n" \
                               #which ": " insn "\n"                     \

xen/arch/x86/x86_emulate/x86_emulate.c

@@ -2211,6 +2211,17 @@ x86_decode(
                     break;
                 }
                 break;
+            case 0x20: /* mov cr,reg */
+            case 0x21: /* mov dr,reg */
+            case 0x22: /* mov reg,cr */
+            case 0x23: /* mov reg,dr */
+                /*
+                 * Mov to/from cr/dr ignore the encoding of Mod, and behave as
+                 * if they were encoded as reg/reg instructions.  No futher
+                 * disp/SIB bytes are fetched.
+                 */
+                modrm_mod = 3;
+                break;
             }
             break;
 
@@ -4759,7 +4770,7 @@ x86_emulate(
     case X86EMUL_OPC(0x0f, 0x21): /* mov dr,reg */
     case X86EMUL_OPC(0x0f, 0x22): /* mov reg,cr */
     case X86EMUL_OPC(0x0f, 0x23): /* mov reg,dr */
-        generate_exception_if(ea.type != OP_REG, EXC_UD, -1);
+        ASSERT(ea.type == OP_REG); /* Early operand adjustment ensures this. */
         generate_exception_if(!mode_ring0(), EXC_GP, 0);
         modrm_reg |= lock_prefix << 3;
         if ( b & 2 )