x86/emulate: add support for {,v}movq xmm,xmm/m64

From: Mihai Donțu <mdontu@bitdefender.com>

Signed-off-by: Mihai Donțu <mdontu@bitdefender.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

diff --git a/tools/tests/x86_emulator/test_x86_emulator.c b/tools/tests/x86_emulator/test_x86_emulator.c
index 9fdf7a73a3777915b8682ab993604d4cee0f0960..f8f17fa9bd0a42d184d511d3ede724eee2a4ca70 100644 (file)
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -713,6 +713,54 @@ int main(int argc, char **argv)
     else
         printf("skipped\n");
 
+    printf("%-40s", "Testing movq %%xmm0,32(%%ecx)...");
+    if ( stack_exec && cpu_has_sse2 )
+    {
+        decl_insn(movq_to_mem2);
+
+        asm volatile ( "pcmpgtb %%xmm0, %%xmm0\n"
+                       put_insn(movq_to_mem2, "movq %%xmm0, 32(%0)")
+                       :: "c" (NULL) );
+
+        memset(res, 0xbd, 64);
+        set_insn(movq_to_mem2);
+        regs.ecx = (unsigned long)res;
+        regs.edx = 0;
+        rc = x86_emulate(&ctxt, &emulops);
+        if ( rc != X86EMUL_OKAY || !check_eip(movq_to_mem2) ||
+             *((uint64_t *)res + 4) ||
+             memcmp(res, res + 10, 24) ||
+             memcmp(res, res + 6, 8) )
+            goto fail;
+        printf("okay\n");
+    }
+    else
+        printf("skipped\n");
+
+    printf("%-40s", "Testing vmovq %%xmm1,32(%%edx)...");
+    if ( stack_exec && cpu_has_avx )
+    {
+        decl_insn(vmovq_to_mem);
+
+        asm volatile ( "pcmpgtb %%xmm1, %%xmm1\n"
+                       put_insn(vmovq_to_mem, "vmovq %%xmm1, 32(%0)")
+                       :: "d" (NULL) );
+
+        memset(res, 0xdb, 64);
+        set_insn(vmovq_to_mem);
+        regs.ecx = 0;
+        regs.edx = (unsigned long)res;
+        rc = x86_emulate(&ctxt, &emulops);
+        if ( rc != X86EMUL_OKAY || !check_eip(vmovq_to_mem) ||
+             *((uint64_t *)res + 4) ||
+             memcmp(res, res + 10, 24) ||
+             memcmp(res, res + 6, 8) )
+            goto fail;
+        printf("okay\n");
+    }
+    else
+        printf("skipped\n");
+
     printf("%-40s", "Testing movdqu %xmm2,(%ecx)...");
     if ( stack_exec && cpu_has_sse2 )
     {

diff --git a/xen/arch/x86/x86_emulate/x86_emulate.c b/xen/arch/x86/x86_emulate/x86_emulate.c
index 8c6cc50bec084a8d0ffa0ca6c5347c1dad582f6d..10c252e60e554bdb997dfa58da9e4a291619d85a 100644 (file)
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -269,7 +269,7 @@ static const opcode_desc_t twobyte_table[256] = {
     ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
     ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
     /* 0xD0 - 0xDF */
-    ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ModRM,
+    ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ImplicitOps|ModRM, ModRM,
     ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ModRM,
     /* 0xE0 - 0xEF */
     ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ModRM, ImplicitOps|ModRM,
@@ -4696,6 +4696,8 @@ x86_emulate(
     case X86EMUL_OPC_F3(0x0f, 0x7f):     /* movdqu xmm,xmm/m128 */
     case X86EMUL_OPC_VEX_F3(0x0f, 0x7f): /* vmovdqu xmm,xmm/m128 */
                                          /* vmovdqu ymm,ymm/m256 */
+    case X86EMUL_OPC_66(0x0f, 0xd6):     /* movq xmm,xmm/m64 */
+    case X86EMUL_OPC_VEX_66(0x0f, 0xd6): /* vmovq xmm,xmm/m64 */
     {
         uint8_t *buf = get_stub(stub);
         struct fpu_insn_ctxt fic = { .insn_bytes = 5 };
@@ -4713,7 +4715,8 @@ x86_emulate(
             case vex_66:
             case vex_f3:
                 host_and_vcpu_must_have(sse2);
-                buf[0] = 0x66; /* movdqa */
+                /* Converting movdqu to movdqa here: Our buffer is aligned. */
+                buf[0] = 0x66;
                 get_fpu(X86EMUL_FPU_xmm, &fic);
                 ea.bytes = 16;
                 break;
@@ -4736,6 +4739,11 @@ x86_emulate(
             get_fpu(X86EMUL_FPU_ymm, &fic);
             ea.bytes = 16 << vex.l;
         }
+        if ( b == 0xd6 )
+        {
+            generate_exception_if(vex.l, EXC_UD, -1);
+            ea.bytes = 8;
+        }
         if ( ea.type == OP_MEM )
         {
             generate_exception_if((vex.pfx == vex_66) &&