qemu-kvm/SOURCES/kvm-x86-Add-AMX-CPUIDs-enumeration.patch

136 lines
4.7 KiB
Diff
Raw Permalink Normal View History

From d0826a8c2c3c389eeeed1014d7e316f39f083971 Mon Sep 17 00:00:00 2001
From: Jing Liu <jing2.liu@intel.com>
Date: Wed, 16 Feb 2022 22:04:31 -0800
Subject: [PATCH 09/24] x86: Add AMX CPUIDs enumeration
RH-Author: Paul Lai <plai@redhat.com>
RH-MergeRequest: 176: Enable KVM AMX support
RH-Commit: [9/13] fab147992ad927c9538529f018f06e2f48546c5b
RH-Bugzilla: 1916415
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Add AMX primary feature bits XFD and AMX_TILE to
enumerate the CPU's AMX capability. Meanwhile, add
AMX TILE and TMUL CPUID leaf and subleaves which
exist when AMX TILE is present to provide the maximum
capability of TILE and TMUL.
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-6-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit f21a48171cf3fa39532fc8553fd82e81b88b6474)
Signed-off-by: Paul Lai <plai@redhat.com>
---
target/i386/cpu.c | 55 ++++++++++++++++++++++++++++++++++++++++---
target/i386/kvm/kvm.c | 4 +++-
2 files changed, 55 insertions(+), 4 deletions(-)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index cd27c0eb81..09e08f7f38 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -574,6 +574,18 @@ static CPUCacheInfo legacy_l3_cache = {
#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */
#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */
+/* CPUID Leaf 0x1D constants: */
+#define INTEL_AMX_TILE_MAX_SUBLEAF 0x1
+#define INTEL_AMX_TOTAL_TILE_BYTES 0x2000
+#define INTEL_AMX_BYTES_PER_TILE 0x400
+#define INTEL_AMX_BYTES_PER_ROW 0x40
+#define INTEL_AMX_TILE_MAX_NAMES 0x8
+#define INTEL_AMX_TILE_MAX_ROWS 0x10
+
+/* CPUID Leaf 0x1E constants: */
+#define INTEL_AMX_TMUL_MAX_K 0x10
+#define INTEL_AMX_TMUL_MAX_N 0x40
+
void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
uint32_t vendor2, uint32_t vendor3)
{
@@ -843,8 +855,8 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
"avx512-vp2intersect", NULL, "md-clear", NULL,
NULL, NULL, "serialize", NULL,
"tsx-ldtrk", NULL, NULL /* pconfig */, NULL,
- NULL, NULL, NULL, "avx512-fp16",
- NULL, NULL, "spec-ctrl", "stibp",
+ NULL, NULL, "amx-bf16", "avx512-fp16",
+ "amx-tile", "amx-int8", "spec-ctrl", "stibp",
NULL, "arch-capabilities", "core-capability", "ssbd",
},
.cpuid = {
@@ -909,7 +921,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
.type = CPUID_FEATURE_WORD,
.feat_names = {
"xsaveopt", "xsavec", "xgetbv1", "xsaves",
- NULL, NULL, NULL, NULL,
+ "xfd", NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
@@ -5593,6 +5605,43 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
}
break;
}
+ case 0x1D: {
+ /* AMX TILE */
+ *eax = 0;
+ *ebx = 0;
+ *ecx = 0;
+ *edx = 0;
+ if (!(env->features[FEAT_7_0_EDX] & CPUID_7_0_EDX_AMX_TILE)) {
+ break;
+ }
+
+ if (count == 0) {
+ /* Highest numbered palette subleaf */
+ *eax = INTEL_AMX_TILE_MAX_SUBLEAF;
+ } else if (count == 1) {
+ *eax = INTEL_AMX_TOTAL_TILE_BYTES |
+ (INTEL_AMX_BYTES_PER_TILE << 16);
+ *ebx = INTEL_AMX_BYTES_PER_ROW | (INTEL_AMX_TILE_MAX_NAMES << 16);
+ *ecx = INTEL_AMX_TILE_MAX_ROWS;
+ }
+ break;
+ }
+ case 0x1E: {
+ /* AMX TMUL */
+ *eax = 0;
+ *ebx = 0;
+ *ecx = 0;
+ *edx = 0;
+ if (!(env->features[FEAT_7_0_EDX] & CPUID_7_0_EDX_AMX_TILE)) {
+ break;
+ }
+
+ if (count == 0) {
+ /* Highest numbered palette subleaf */
+ *ebx = INTEL_AMX_TMUL_MAX_K | (INTEL_AMX_TMUL_MAX_N << 8);
+ }
+ break;
+ }
case 0x40000000:
/*
* CPUID code in kvm_arch_init_vcpu() ignores stuff
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index b5d98c4361..a64a79d870 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -1779,7 +1779,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
c = &cpuid_data.entries[cpuid_i++];
}
break;
- case 0x14: {
+ case 0x14:
+ case 0x1d:
+ case 0x1e: {
uint32_t times;
c->function = i;
--
2.35.3