[PATCH v2 16/17] x86emul: support TILERELEASE

[Jan Beulich <jbeulich@xxxxxxxx>]

This is relatively straightforward, and hence best suited to introduce a
few other general pieces.

Testing of this will be added once a sensible test can be put together,
i.e. when support for other insns is also there.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
v2: New.

--- a/tools/tests/x86_emulator/predicates.c
+++ b/tools/tests/x86_emulator/predicates.c
@@ -1335,6 +1335,7 @@ static const struct vex {
     { { 0x45 }, 2, T, R, pfx_66, Wn, Ln }, /* vpsrlv{d,q} */
     { { 0x46 }, 2, T, R, pfx_66, W0, Ln }, /* vpsravd */
     { { 0x47 }, 2, T, R, pfx_66, Wn, Ln }, /* vpsllv{d,q} */
+    { { 0x49, 0xc0 }, 2, F, N, pfx_no, W0, L0 }, /* tilerelease */
     { { 0x50 }, 2, T, R, pfx_66, W0, Ln }, /* vpdpbusd */
     { { 0x51 }, 2, T, R, pfx_66, W0, Ln }, /* vpdpbusds */
     { { 0x52 }, 2, T, R, pfx_66, W0, Ln }, /* vpdpwssd */
--- a/tools/tests/x86_emulator/x86-emulate.c
+++ b/tools/tests/x86_emulator/x86-emulate.c
@@ -247,6 +247,9 @@ int emul_test_get_fpu(
             break;
     default:
         return X86EMUL_UNHANDLEABLE;
+
+    case X86EMUL_FPU_tile:
+        return cpu_has_amx_tile ? X86EMUL_OKAY : X86EMUL_UNHANDLEABLE;
     }
     return X86EMUL_OKAY;
 }
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -475,6 +475,7 @@ static const struct ext0f38_table {
     [0x43] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
     [0x44] = { .simd_size = simd_packed_int, .two_op = 1, .d8s = d8s_vl },
     [0x45 ... 0x47] = { .simd_size = simd_packed_int, .d8s = d8s_vl },
+    [0x49] = { .simd_size = simd_other, .two_op = 1 },
     [0x4c] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl },
     [0x4d] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
     [0x4e] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl },
@@ -2014,6 +2015,7 @@ amd_like(const struct x86_emulate_ctxt *
 #define vcpu_has_avx512_4fmaps() (ctxt->cpuid->feat.avx512_4fmaps)
 #define vcpu_has_avx512_vp2intersect() (ctxt->cpuid->feat.avx512_vp2intersect)
 #define vcpu_has_serialize()   (ctxt->cpuid->feat.serialize)
+#define vcpu_has_amx_tile()    (ctxt->cpuid->feat.amx_tile)
 #define vcpu_has_avx_vnni()    (ctxt->cpuid->feat.avx_vnni)
 #define vcpu_has_avx512_bf16() (ctxt->cpuid->feat.avx512_bf16)
 
@@ -9460,6 +9462,24 @@ x86_emulate(
         generate_exception_if(vex.l, EXC_UD);
         goto simd_0f_avx;
 
+    case X86EMUL_OPC_VEX(0x0f38, 0x49):
+        generate_exception_if(!mode_64bit() || vex.l || vex.w, EXC_UD);
+        if ( ea.type == OP_REG )
+        {
+            switch ( modrm )
+            {
+            case 0xc0: /* tilerelease */
+                host_and_vcpu_must_have(amx_tile);
+                get_fpu(X86EMUL_FPU_tile);
+                op_bytes = 1; /* fake */
+                goto simd_0f_common;
+
+            default:
+                goto unrecognized_insn;
+            }
+        }
+        goto unimplemented_insn;
+
     case X86EMUL_OPC_VEX_66(0x0f38, 0x50): /* vpdpbusd 
[xy]mm/mem,[xy]mm,[xy]mm */
     case X86EMUL_OPC_VEX_66(0x0f38, 0x51): /* vpdpbusds 
[xy]mm/mem,[xy]mm,[xy]mm */
     case X86EMUL_OPC_VEX_66(0x0f38, 0x52): /* vpdpwssd 
[xy]mm/mem,[xy]mm,[xy]mm */
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -131,6 +131,7 @@
 #define cpu_has_avx512_vp2intersect 
boot_cpu_has(X86_FEATURE_AVX512_VP2INTERSECT)
 #define cpu_has_tsx_force_abort boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)
 #define cpu_has_serialize       boot_cpu_has(X86_FEATURE_SERIALIZE)
+#define cpu_has_amx_tile        boot_cpu_has(X86_FEATURE_AMX_TILE)
 
 /* CPUID level 0x00000007:1.eax */
 #define cpu_has_avx_vnni        boot_cpu_has(X86_FEATURE_AVX_VNNI)