[PATCH v2 2/8] x86: Add AMX XTILECFG and XTILEDATA components

[Yang Zhong <yang.zhong@intel.com>]

From: Jing Liu <jing2.liu@intel.com>

The AMX TILECFG register and the TMMx tile data registers are
saved/restored via XSAVE, respectively in state component 17
(64 bytes) and state component 18 (8192 bytes).

Add AMX feature bits to x86_ext_save_areas array to set
up AMX components. Add structs that define the layout of
AMX XSAVE areas and use QEMU_BUILD_BUG_ON to validate the
structs sizes.

Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
---
 target/i386/cpu.h | 18 +++++++++++++++++-
 target/i386/cpu.c |  8 ++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index de1dc124ab..06d2d6bccf 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -537,6 +537,8 @@ typedef enum X86Seg {
 #define XSTATE_ZMM_Hi256_BIT            6
 #define XSTATE_Hi16_ZMM_BIT             7
 #define XSTATE_PKRU_BIT                 9
+#define XSTATE_XTILE_CFG_BIT            17
+#define XSTATE_XTILE_DATA_BIT           18
 
 #define XSTATE_FP_MASK                  (1ULL << XSTATE_FP_BIT)
 #define XSTATE_SSE_MASK                 (1ULL << XSTATE_SSE_BIT)
@@ -845,6 +847,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS];
 #define CPUID_7_0_EDX_TSX_LDTRK         (1U << 16)
 /* AVX512_FP16 instruction */
 #define CPUID_7_0_EDX_AVX512_FP16       (1U << 23)
+/* AMX tile (two-dimensional register) */
+#define CPUID_7_0_EDX_AMX_TILE          (1U << 24)
 /* Speculation Control */
 #define CPUID_7_0_EDX_SPEC_CTRL         (1U << 26)
 /* Single Thread Indirect Branch Predictors */
@@ -1348,6 +1352,16 @@ typedef struct XSavePKRU {
     uint32_t padding;
 } XSavePKRU;
 
+/* Ext. save area 17: AMX XTILECFG state */
+typedef struct XSaveXTILECFG {
+    uint8_t xtilecfg[64];
+} XSaveXTILECFG;
+
+/* Ext. save area 18: AMX XTILEDATA state */
+typedef struct XSaveXTILEDATA {
+    uint8_t xtiledata[8][1024];
+} XSaveXTILEDATA;
+
 QEMU_BUILD_BUG_ON(sizeof(XSaveAVX) != 0x100);
 QEMU_BUILD_BUG_ON(sizeof(XSaveBNDREG) != 0x40);
 QEMU_BUILD_BUG_ON(sizeof(XSaveBNDCSR) != 0x40);
@@ -1355,6 +1369,8 @@ QEMU_BUILD_BUG_ON(sizeof(XSaveOpmask) != 0x40);
 QEMU_BUILD_BUG_ON(sizeof(XSaveZMM_Hi256) != 0x200);
 QEMU_BUILD_BUG_ON(sizeof(XSaveHi16_ZMM) != 0x400);
 QEMU_BUILD_BUG_ON(sizeof(XSavePKRU) != 0x8);
+QEMU_BUILD_BUG_ON(sizeof(XSaveXTILECFG) != 0x40);
+QEMU_BUILD_BUG_ON(sizeof(XSaveXTILEDATA) != 0x2000);
 
 typedef struct ExtSaveArea {
     uint32_t feature, bits;
@@ -1362,7 +1378,7 @@ typedef struct ExtSaveArea {
     uint32_t ecx;
 } ExtSaveArea;
 
-#define XSAVE_STATE_AREA_COUNT (XSTATE_PKRU_BIT + 1)
+#define XSAVE_STATE_AREA_COUNT (XSTATE_XTILE_DATA_BIT + 1)
 
 extern ExtSaveArea x86_ext_save_areas[XSAVE_STATE_AREA_COUNT];
 
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 37f06b0b1a..ea7e8f9081 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1401,6 +1401,14 @@ ExtSaveArea x86_ext_save_areas[XSAVE_STATE_AREA_COUNT] = {
     [XSTATE_PKRU_BIT] =
           { .feature = FEAT_7_0_ECX, .bits = CPUID_7_0_ECX_PKU,
             .size = sizeof(XSavePKRU) },
+    [XSTATE_XTILE_CFG_BIT] = {
+        .feature = FEAT_7_0_EDX, .bits = CPUID_7_0_EDX_AMX_TILE,
+        .size = sizeof(XSaveXTILECFG),
+    },
+    [XSTATE_XTILE_DATA_BIT] = {
+        .feature = FEAT_7_0_EDX, .bits = CPUID_7_0_EDX_AMX_TILE,
+        .size = sizeof(XSaveXTILEDATA)
+    },
 };
 
 static uint32_t xsave_area_size(uint64_t mask)