|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-changelog] [xen-unstable] x86/emulator: add emulation of SIMD FP moves
# HG changeset patch
# User Jan Beulich <jbeulich@xxxxxxxx>
# Date 1322725771 -3600
# Node ID 07cf778d517fdf661a34027af653a489489bf222
# Parent 73a5655c2ac594017fa2aa066d06000417fbba76
x86/emulator: add emulation of SIMD FP moves
Clone the existing movq emulation to also support the most fundamental
SIMD FP moves.
Extend the testing code to also exercise these instructions.
Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
Acked-by: Keir Fraser <keir@xxxxxxx>
---
diff -r 73a5655c2ac5 -r 07cf778d517f
tools/tests/x86_emulator/test_x86_emulator.c
--- a/tools/tests/x86_emulator/test_x86_emulator.c Thu Dec 01 08:48:14
2011 +0100
+++ b/tools/tests/x86_emulator/test_x86_emulator.c Thu Dec 01 08:49:31
2011 +0100
@@ -629,6 +629,60 @@
else
printf("skipped\n");
+ printf("%-40s", "Testing movsd %xmm5,(%ecx)...");
+ memset(res, 0x77, 64);
+ memset(res + 10, 0x66, 8);
+ if ( stack_exec && cpu_has_sse2 )
+ {
+ extern const unsigned char movsd_to_mem[];
+
+ asm volatile ( "movlpd %0, %%xmm5\n\t"
+ "movhpd %0, %%xmm5\n"
+ ".pushsection .test, \"a\", @progbits\n"
+ "movsd_to_mem: movsd %%xmm5, (%1)\n"
+ ".popsection" :: "m" (res[10]), "c" (NULL) );
+
+ memcpy(instr, movsd_to_mem, 15);
+ regs.eip = (unsigned long)&instr[0];
+ regs.ecx = (unsigned long)(res + 2);
+ regs.edx = 0;
+ rc = x86_emulate(&ctxt, &emulops);
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+ goto fail;
+ printf("okay\n");
+ }
+ else
+ {
+ printf("skipped\n");
+ memset(res + 2, 0x66, 8);
+ }
+
+ printf("%-40s", "Testing movaps (%edx),%xmm7...");
+ if ( stack_exec && cpu_has_sse )
+ {
+ extern const unsigned char movaps_from_mem[];
+
+ asm volatile ( "xorps %%xmm7, %%xmm7\n"
+ ".pushsection .test, \"a\", @progbits\n"
+ "movaps_from_mem: movaps (%0), %%xmm7\n"
+ ".popsection" :: "d" (NULL) );
+
+ memcpy(instr, movaps_from_mem, 15);
+ regs.eip = (unsigned long)&instr[0];
+ regs.ecx = 0;
+ regs.edx = (unsigned long)res;
+ rc = x86_emulate(&ctxt, &emulops);
+ if ( rc != X86EMUL_OKAY )
+ goto fail;
+ asm ( "cmpeqps %1, %%xmm7\n\t"
+ "movmskps %%xmm7, %0" : "=r" (rc) : "m" (res[8]) );
+ if ( rc != 0xf )
+ goto fail;
+ printf("okay\n");
+ }
+ else
+ printf("skipped\n");
+
for ( j = 1; j <= 2; j++ )
{
#if defined(__i386__)
diff -r 73a5655c2ac5 -r 07cf778d517f xen/arch/x86/x86_emulate/x86_emulate.c
--- a/xen/arch/x86/x86_emulate/x86_emulate.c Thu Dec 01 08:48:14 2011 +0100
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c Thu Dec 01 08:49:31 2011 +0100
@@ -176,7 +176,7 @@
/* 0x08 - 0x0F */
ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps|ModRM, 0, 0,
/* 0x10 - 0x17 */
- 0, 0, 0, 0, 0, 0, 0, 0,
+ ImplicitOps|ModRM, ImplicitOps|ModRM, 0, 0, 0, 0, 0, 0,
/* 0x18 - 0x1F */
ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM,
ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM,
@@ -184,7 +184,7 @@
ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM, ImplicitOps|ModRM,
0, 0, 0, 0,
/* 0x28 - 0x2F */
- 0, 0, 0, 0, 0, 0, 0, 0,
+ ImplicitOps|ModRM, ImplicitOps|ModRM, 0, ImplicitOps|ModRM, 0, 0, 0, 0,
/* 0x30 - 0x37 */
ImplicitOps, ImplicitOps, ImplicitOps, 0,
ImplicitOps, ImplicitOps, 0, 0,
@@ -273,6 +273,16 @@
vex_f2
};
+#define VEX_PREFIX_DOUBLE_MASK 0x1
+#define VEX_PREFIX_SCALAR_MASK 0x2
+
+static const uint8_t sse_prefix[] = { 0x66, 0xf3, 0xf2 };
+
+#define SET_SSE_PREFIX(dst, vex_pfx) do { \
+ if ( vex_pfx ) \
+ (dst) = sse_prefix[(vex_pfx) - 1]; \
+} while (0)
+
union vex {
uint8_t raw[2];
struct {
@@ -3850,6 +3860,76 @@
case 0x19 ... 0x1f: /* nop (amd-defined) */
break;
+ case 0x2b: /* {,v}movntp{s,d} xmm,m128 */
+ /* vmovntp{s,d} ymm,m256 */
+ fail_if(ea.type != OP_MEM);
+ /* fall through */
+ case 0x28: /* {,v}movap{s,d} xmm/m128,xmm */
+ /* vmovap{s,d} ymm/m256,ymm */
+ case 0x29: /* {,v}movap{s,d} xmm,xmm/m128 */
+ /* vmovap{s,d} ymm,ymm/m256 */
+ fail_if(vex.pfx & VEX_PREFIX_SCALAR_MASK);
+ /* fall through */
+ case 0x10: /* {,v}movup{s,d} xmm/m128,xmm */
+ /* vmovup{s,d} ymm/m256,ymm */
+ /* {,v}movss xmm/m32,xmm */
+ /* {,v}movsd xmm/m64,xmm */
+ case 0x11: /* {,v}movup{s,d} xmm,xmm/m128 */
+ /* vmovup{s,d} ymm,ymm/m256 */
+ /* {,v}movss xmm,xmm/m32 */
+ /* {,v}movsd xmm,xmm/m64 */
+ {
+ uint8_t stub[] = { 0x3e, 0x3e, 0x0f, b, modrm, 0xc3 };
+ struct fpu_insn_ctxt fic = { .insn_bytes = sizeof(stub)-1 };
+
+ if ( vex.opcx == vex_none )
+ {
+ if ( vex.pfx & VEX_PREFIX_DOUBLE_MASK )
+ vcpu_must_have_sse2();
+ else
+ vcpu_must_have_sse();
+ ea.bytes = 16;
+ SET_SSE_PREFIX(stub[0], vex.pfx);
+ get_fpu(X86EMUL_FPU_xmm, &fic);
+ }
+ else
+ {
+ fail_if((vex.opcx != vex_0f) ||
+ (vex.reg && ((ea.type == OP_MEM) ||
+ !(vex.pfx & VEX_PREFIX_SCALAR_MASK))));
+ vcpu_must_have_avx();
+ get_fpu(X86EMUL_FPU_ymm, &fic);
+ ea.bytes = 16 << vex.l;
+ }
+ if ( vex.pfx & VEX_PREFIX_SCALAR_MASK )
+ ea.bytes = vex.pfx & VEX_PREFIX_DOUBLE_MASK ? 8 : 4;
+ if ( ea.type == OP_MEM )
+ {
+ /* XXX enable once there is ops->ea() or equivalent
+ generate_exception_if((b >= 0x28) &&
+ (ops->ea(ea.mem.seg, ea.mem.off)
+ & (ea.bytes - 1)), EXC_GP, 0); */
+ if ( !(b & 1) )
+ rc = ops->read(ea.mem.seg, ea.mem.off+0, mmvalp,
+ ea.bytes, ctxt);
+ /* convert memory operand to (%rAX) */
+ rex_prefix &= ~REX_B;
+ vex.b = 1;
+ stub[4] &= 0x38;
+ }
+ if ( !rc )
+ {
+ copy_REX_VEX(stub, rex_prefix, vex);
+ asm volatile ( "call *%0" : : "r" (stub), "a" (mmvalp)
+ : "memory" );
+ }
+ put_fpu(&fic);
+ if ( !rc && (b & 1) && (ea.type == OP_MEM) )
+ rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp,
+ ea.bytes, ctxt);
+ goto done;
+ }
+
case 0x20: /* mov cr,reg */
case 0x21: /* mov dr,reg */
case 0x22: /* mov reg,cr */
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |