[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH] x86emul: no need to set fault_suppression to false for VMOVNT*
When evex.opmsk is required to be zero there's no need for this, as it won't have been set to true in the first place. Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx> --- I've made similar changes to patches 16, 45, and 46 of v7 of the main AVX512 series. --- a/xen/arch/x86/x86_emulate/x86_emulate.c +++ b/xen/arch/x86/x86_emulate/x86_emulate.c @@ -5911,7 +5911,6 @@ x86_emulate( CASE_SIMD_PACKED_FP(_EVEX, 0x0f, 0x2b): /* vmovntp{s,d} [xyz]mm,mem */ generate_exception_if(ea.type != OP_MEM || evex.opmsk, EXC_UD); sfence = true; - fault_suppression = false; /* fall through */ CASE_SIMD_PACKED_FP(_EVEX, 0x0f, 0x10): /* vmovup{s,d} [xyz]mm/mem,[xyz]mm{k} */ CASE_SIMD_SCALAR_FP(_EVEX, 0x0f, 0x10): /* vmovs{s,d} mem,xmm{k} */ @@ -6793,7 +6792,6 @@ x86_emulate( generate_exception_if(ea.type != OP_MEM || evex.opmsk || evex.w, EXC_UD); sfence = true; - fault_suppression = false; /* fall through */ case X86EMUL_OPC_EVEX_66(0x0f, 0x6f): /* vmovdqa{32,64} [xyz]mm/mem,[xyz]mm{k} */ case X86EMUL_OPC_EVEX_F3(0x0f, 0x6f): /* vmovdqu{32,64} [xyz]mm/mem,[xyz]mm{k} */ _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxxx https://lists.xenproject.org/mailman/listinfo/xen-devel
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |