[PATCH] x86emul: fix VPBLENDMW with mask and memory operand

[Jan Beulich <jbeulich@xxxxxxxx>]

Element size for this opcode depends on EVEX.W, not the low opcode bit.
Make use of AVX512BW being a prereq to AVX512_BITALG and move the case
label there, adding an AVX512BW feature check.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>

--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -7401,7 +7401,6 @@ x86_emulate(
     case X86EMUL_OPC_EVEX_66(0x0f38, 0x0b): /* vpmulhrsw 
[xyz]mm/mem,[xyz]mm,[xyz]mm{k} */
     case X86EMUL_OPC_EVEX_66(0x0f38, 0x1c): /* vpabsb [xyz]mm/mem,[xyz]mm{k} */
     case X86EMUL_OPC_EVEX_66(0x0f38, 0x1d): /* vpabsw [xyz]mm/mem,[xyz]mm{k} */
-    case X86EMUL_OPC_EVEX_66(0x0f38, 0x66): /* vpblendm{b,w} 
[xyz]mm/mem,[xyz]mm,[xyz]mm{k} */
         host_and_vcpu_must_have(avx512bw);
         generate_exception_if(evex.brs, EXC_UD);
         elem_bytes = 1 << (b & 1);
@@ -9558,6 +9557,9 @@ x86_emulate(
         /* fall through */
     case X86EMUL_OPC_EVEX_66(0x0f38, 0x54): /* vpopcnt{b,w} 
[xyz]mm/mem,[xyz]mm{k} */
         host_and_vcpu_must_have(avx512_bitalg);
+        /* fall through */
+    case X86EMUL_OPC_EVEX_66(0x0f38, 0x66): /* vpblendm{b,w} 
[xyz]mm/mem,[xyz]mm,[xyz]mm{k} */
+        host_and_vcpu_must_have(avx512bw);
         generate_exception_if(evex.brs, EXC_UD);
         elem_bytes = 1 << evex.w;
         goto avx512f_no_sae;