|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v3 13/18] x86emul: support SSSE3 insns
... and their AVX equivalents.
Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
v3: New.
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -343,6 +343,8 @@ static const struct {
uint8_t two_op:1;
uint8_t vsib:1;
} ext0f38_table[256] = {
+ [0x00 ... 0x0b] = { .simd_size = simd_packed_int },
+ [0x1c ... 0x1e] = { .simd_size = simd_packed_int, .two_op = 1 },
[0x2a] = { .simd_size = simd_packed_int, .two_op = 1 },
[0xf0] = { .two_op = 1 },
[0xf1] = { .to_memory = 1, .two_op = 1 },
@@ -356,6 +358,7 @@ static const struct {
uint8_t two_op:1;
uint8_t four_op:1;
} ext0f3a_table[256] = {
+ [0x0f] = { .simd_size = simd_packed_int },
[0xf0] = {},
};
@@ -1416,6 +1419,7 @@ static bool vcpu_has(
#define vcpu_has_sse() vcpu_has( 1, EDX, 25, ctxt, ops)
#define vcpu_has_sse2() vcpu_has( 1, EDX, 26, ctxt, ops)
#define vcpu_has_sse3() vcpu_has( 1, ECX, 0, ctxt, ops)
+#define vcpu_has_ssse3() vcpu_has( 1, ECX, 9, ctxt, ops)
#define vcpu_has_cx16() vcpu_has( 1, ECX, 13, ctxt, ops)
#define vcpu_has_sse4_1() vcpu_has( 1, ECX, 19, ctxt, ops)
#define vcpu_has_sse4_2() vcpu_has( 1, ECX, 20, ctxt, ops)
@@ -5909,6 +5913,21 @@ x86_emulate(
simd_0f_int:
if ( vex.opcx != vex_none )
{
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x00): /* vpshufb
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x01): /* vphaddw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x02): /* vphaddd
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x03): /* vphaddsw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x04): /* vpmaddubsw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x05): /* vphsubw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x06): /* vphsubd
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x07): /* vphsubsw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x08): /* vpsignb
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x09): /* vpsignw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x0a): /* vpsignd
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x0b): /* vpmulhrsw
{x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x1c): /* vpabsb {x,y}mm/mem,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x1d): /* vpabsw {x,y}mm/mem,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x1e): /* vpabsd {x,y}mm/mem,{x,y}mm */
if ( !vex.l )
goto simd_0f_avx;
host_and_vcpu_must_have(avx2);
@@ -6004,6 +6023,7 @@ x86_emulate(
simd_0f_int_imm8:
if ( vex.opcx != vex_none )
{
+ case X86EMUL_OPC_VEX_66(0x0f3a, 0x0f): /* vpalignr
$imm8,{x,y}mm/mem,{x,y}mm,{x,y}mm */
if ( vex.l )
host_and_vcpu_must_have(avx2);
else
@@ -6871,6 +6891,58 @@ x86_emulate(
sfence = true;
break;
+ case X86EMUL_OPC(0x0f38, 0x00): /* pshufb mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x00): /* pshufb xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x01): /* phaddw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x01): /* phaddw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x02): /* phaddd mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x02): /* phaddd xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x03): /* phaddsw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x03): /* phaddsw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x04): /* pmaddubsw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x04): /* pmaddubsw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x05): /* phsubw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x05): /* phsubw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x06): /* phsubd mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x06): /* phsubd xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x07): /* phsubsw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x07): /* phsubsw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x08): /* psignb mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x08): /* psignb xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x09): /* psignw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x09): /* psignw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x0a): /* psignd mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x0a): /* psignd xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x0b): /* pmulhrsw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x0b): /* pmulhrsw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x1c): /* pabsb mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x1c): /* pabsb xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x1d): /* pabsw mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x1d): /* pabsw xmm/m128,xmm */
+ case X86EMUL_OPC(0x0f38, 0x1e): /* pabsd mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f38, 0x1e): /* pabsd xmm/m128,xmm */
+ host_and_vcpu_must_have(ssse3);
+ if ( vex.pfx )
+ get_fpu(X86EMUL_FPU_xmm, &fic);
+ else
+ {
+ host_and_vcpu_must_have(mmx);
+ get_fpu(X86EMUL_FPU_mmx, &fic);
+ }
+ opc = init_prefixes(stub);
+ opc[0] = 0x38;
+ opc[1] = b;
+ opc[2] = modrm;
+ if ( ea.type == OP_MEM )
+ {
+ /* Convert memory operand to (%rAX). */
+ rex_prefix &= ~REX_B;
+ vex.b = 1;
+ opc[2] &= 0x38;
+ }
+ fic.insn_bytes = PFX_BYTES + 3;
+ break;
+
case X86EMUL_OPC_66(0x0f38, 0x2a): /* movntdqa m128,xmm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x2a): /* vmovntdqa mem,{x,y}mm */
generate_exception_if(ea.type != OP_MEM, EXC_UD);
@@ -7052,6 +7124,31 @@ x86_emulate(
: "0" ((uint32_t)src.val), "rm" (_regs._edx) );
break;
+ case X86EMUL_OPC(0x0f3a, 0x0f): /* palignr $imm8,mm/m64,mm */
+ case X86EMUL_OPC_66(0x0f3a, 0x0f): /* palignr $imm8,xmm/m128,xmm */
+ host_and_vcpu_must_have(ssse3);
+ if ( vex.pfx )
+ get_fpu(X86EMUL_FPU_xmm, &fic);
+ else
+ {
+ host_and_vcpu_must_have(mmx);
+ get_fpu(X86EMUL_FPU_mmx, &fic);
+ }
+ opc = init_prefixes(stub);
+ opc[0] = 0x3a;
+ opc[1] = b;
+ opc[2] = modrm;
+ if ( ea.type == OP_MEM )
+ {
+ /* Convert memory operand to (%rAX). */
+ rex_prefix &= ~REX_B;
+ vex.b = 1;
+ opc[2] &= 0x38;
+ }
+ opc[3] = imm1;
+ fic.insn_bytes = PFX_BYTES + 4;
+ break;
+
case X86EMUL_OPC_VEX_F2(0x0f3a, 0xf0): /* rorx imm,r/m,r */
vcpu_must_have(bmi2);
generate_exception_if(vex.l || vex.reg != 0xf, EXC_UD);
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -39,6 +39,7 @@
#define cpu_has_mtrr 1
#define cpu_has_mmx boot_cpu_has(X86_FEATURE_MMX)
#define cpu_has_sse3 boot_cpu_has(X86_FEATURE_SSE3)
+#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3)
#define cpu_has_sse4_2 boot_cpu_has(X86_FEATURE_SSE4_2)
#define cpu_has_popcnt boot_cpu_has(X86_FEATURE_POPCNT)
#define cpu_has_htt boot_cpu_has(X86_FEATURE_HTT)
Attachment:
x86emul-SSSE3.patch _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxx https://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |