[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] Re: [Xen-devel] [PATCH v4 3/4] x86emul: Support vaes insns
>>> On 03.01.18 at 09:26, <yang.zhong@xxxxxxxxx> wrote: > The previous aes insns only support legacy and AVX128. > Icelake added AVX256 support. Same remark here as for the pclmulqdq patch. > Signed-off-by: Yang Zhong <yang.zhong@xxxxxxxxx> > --- Please provide a brief list of changes at this spot in each patch. > @@ -7336,17 +7337,23 @@ x86_emulate( > case X86EMUL_OPC_66(0x0f38, 0xdb): /* aesimc xmm/m128,xmm */ > case X86EMUL_OPC_VEX_66(0x0f38, 0xdb): /* vaesimc xmm/m128,xmm */ > case X86EMUL_OPC_66(0x0f38, 0xdc): /* aesenc xmm/m128,xmm,xmm */ > - case X86EMUL_OPC_VEX_66(0x0f38, 0xdc): /* vaesenc xmm/m128,xmm,xmm */ > + case X86EMUL_OPC_VEX_66(0x0f38, 0xdc): /* vaesenc > {x,y}mm/mem,{x,y}mm,{x,y}mm */ > case X86EMUL_OPC_66(0x0f38, 0xdd): /* aesenclast xmm/m128,xmm,xmm */ > - case X86EMUL_OPC_VEX_66(0x0f38, 0xdd): /* vaesenclast xmm/m128,xmm,xmm */ > + case X86EMUL_OPC_VEX_66(0x0f38, 0xdd): /* vaesenclast > {x,y}mm/mem,{x,y}mm,{x,y}mm */ > case X86EMUL_OPC_66(0x0f38, 0xde): /* aesdec xmm/m128,xmm,xmm */ > - case X86EMUL_OPC_VEX_66(0x0f38, 0xde): /* vaesdec xmm/m128,xmm,xmm */ > + case X86EMUL_OPC_VEX_66(0x0f38, 0xde): /* vaesdec > {x,y}mm/mem,{x,y}mm,{x,y}mm */ > case X86EMUL_OPC_66(0x0f38, 0xdf): /* aesdeclast xmm/m128,xmm,xmm */ > - case X86EMUL_OPC_VEX_66(0x0f38, 0xdf): /* vaesdeclast xmm/m128,xmm,xmm */ > + case X86EMUL_OPC_VEX_66(0x0f38, 0xdf): /* vaesdeclast > {x,y}mm/mem,{x,y}mm,{x,y}mm */ > + if ( vex.l ) > + { > + host_and_vcpu_must_have(vaes); > + goto simd_0f_ymm; > + } > host_and_vcpu_must_have(aesni); > if ( vex.opcx == vex_none ) > goto simd_0f38_common; > - /* fall through */ > + goto simd_0f_avx; > + > case X86EMUL_OPC_VEX_66(0x0f38, 0x41): /* vphminposuw xmm/m128,xmm,xmm */ Hmm, you've reacted to my v3 comments, but you didn't really address them: VAESIMC still is mishandled with the code above. Note that I didn't say "remove the fall-through", but instead "move out the block no longer wanting this fall-through". Jan _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxxx https://lists.xenproject.org/mailman/listinfo/xen-devel
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |