target/loongarch: Add LASX data support

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-12-gaosong@loongson.cn>

linux-user/loongarch64/signal.c

@@ -12,6 +12,7 @@
 #include "linux-user/trace.h"
 
 #include "target/loongarch/internals.h"
+#include "target/loongarch/vec.h"
 
 /* FP context was used */
 #define SC_USED_FP              (1 << 0)

target/loongarch/cpu.c

@@ -19,6 +19,7 @@
 #include "cpu-csr.h"
 #include "sysemu/reset.h"
 #include "tcg/tcg.h"
+#include "vec.h"
 
 const char * const regnames[32] = {
     "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7",

target/loongarch/cpu.h

@@ -251,18 +251,20 @@ FIELD(TLB_MISC, ASID, 1, 10)
 FIELD(TLB_MISC, VPPN, 13, 35)
 FIELD(TLB_MISC, PS, 48, 6)
 
-#define LSX_LEN   (128)
+#define LSX_LEN    (128)
+#define LASX_LEN   (256)
+
 typedef union VReg {
-    int8_t   B[LSX_LEN / 8];
+    int8_t   B[LASX_LEN / 8];
-    int16_t  H[LSX_LEN / 16];
+    int16_t  H[LASX_LEN / 16];
-    int32_t  W[LSX_LEN / 32];
+    int32_t  W[LASX_LEN / 32];
-    int64_t  D[LSX_LEN / 64];
+    int64_t  D[LASX_LEN / 64];
-    uint8_t  UB[LSX_LEN / 8];
+    uint8_t  UB[LASX_LEN / 8];
-    uint16_t UH[LSX_LEN / 16];
+    uint16_t UH[LASX_LEN / 16];
-    uint32_t UW[LSX_LEN / 32];
+    uint32_t UW[LASX_LEN / 32];
-    uint64_t UD[LSX_LEN / 64];
+    uint64_t UD[LASX_LEN / 64];
-    Int128   Q[LSX_LEN / 128];
+    Int128   Q[LASX_LEN / 128];
-}VReg;
+} VReg;
 
 typedef union fpr_t fpr_t;
 union fpr_t {

target/loongarch/gdbstub.c

@@ -11,6 +11,7 @@
 #include "internals.h"
 #include "exec/gdbstub.h"
 #include "gdbstub/helpers.h"
+#include "vec.h"
 
 uint64_t read_fcc(CPULoongArchState *env)
 {

target/loongarch/internals.h

@@ -21,28 +21,6 @@
 /* Global bit for huge page */
 #define LOONGARCH_HGLOBAL_SHIFT     12
 
-#if  HOST_BIG_ENDIAN
-#define B(x)  B[15 - (x)]
-#define H(x)  H[7 - (x)]
-#define W(x)  W[3 - (x)]
-#define D(x)  D[1 - (x)]
-#define UB(x) UB[15 - (x)]
-#define UH(x) UH[7 - (x)]
-#define UW(x) UW[3 - (x)]
-#define UD(x) UD[1 -(x)]
-#define Q(x)  Q[x]
-#else
-#define B(x)  B[x]
-#define H(x)  H[x]
-#define W(x)  W[x]
-#define D(x)  D[x]
-#define UB(x) UB[x]
-#define UH(x) UH[x]
-#define UW(x) UW[x]
-#define UD(x) UD[x]
-#define Q(x)  Q[x]
-#endif
-
 void loongarch_translate_init(void);
 
 void loongarch_cpu_dump_state(CPUState *cpu, FILE *f, int flags);

target/loongarch/machine.c

@@ -8,7 +8,7 @@
 #include "qemu/osdep.h"
 #include "cpu.h"
 #include "migration/cpu.h"
-#include "internals.h"
+#include "vec.h"
 
 static const VMStateDescription vmstate_fpu_reg = {
     .name = "fpu_reg",
@@ -76,6 +76,39 @@ static const VMStateDescription vmstate_lsx = {
     },
 };
 
+static const VMStateDescription vmstate_lasxh_reg = {
+    .name = "lasxh_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(UD(2), VReg),
+        VMSTATE_UINT64(UD(3), VReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_LASXH_REGS(_field, _state, _start)          \
+    VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, 32, 0, \
+                             vmstate_lasxh_reg, fpr_t)
+
+static bool lasx_needed(void *opaque)
+{
+    LoongArchCPU *cpu = opaque;
+
+    return FIELD_EX64(cpu->env.cpucfg[2], CPUCFG2, LASX);
+}
+
+static const VMStateDescription vmstate_lasx = {
+    .name = "cpu/lasx",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = lasx_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_LASXH_REGS(env.fpr, LoongArchCPU, 0),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 /* TLB state */
 const VMStateDescription vmstate_tlb = {
     .name = "cpu/tlb",
@@ -163,6 +196,7 @@ const VMStateDescription vmstate_loongarch_cpu = {
     .subsections = (const VMStateDescription*[]) {
         &vmstate_fpu,
         &vmstate_lsx,
+        &vmstate_lasx,
         NULL
     }
 };

target/loongarch/translate.c

@@ -18,6 +18,7 @@
 #include "fpu/softfloat.h"
 #include "translate.h"
 #include "internals.h"
+#include "vec.h"
 
 /* Global register indices */
 TCGv cpu_gpr[32], cpu_pc;

target/loongarch/vec.h

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * QEMU LoongArch vector utilitites
+ *
+ * Copyright (c) 2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef LOONGARCH_VEC_H
+#define LOONGARCH_VEC_H
+
+#if HOST_BIG_ENDIAN
+#define B(x)  B[(x) ^ 15]
+#define H(x)  H[(x) ^ 7]
+#define W(x)  W[(x) ^ 3]
+#define D(x)  D[(x) ^ 1]
+#define UB(x) UB[(x) ^ 15]
+#define UH(x) UH[(x) ^ 7]
+#define UW(x) UW[(x) ^ 3]
+#define UD(x) UD[(x) ^ 1]
+#define Q(x)  Q[x]
+#else
+#define B(x)  B[x]
+#define H(x)  H[x]
+#define W(x)  W[x]
+#define D(x)  D[x]
+#define UB(x) UB[x]
+#define UH(x) UH[x]
+#define UW(x) UW[x]
+#define UD(x) UD[x]
+#define Q(x)  Q[x]
+#endif /* HOST_BIG_ENDIAN */
+
+#endif /* LOONGARCH_VEC_H */

target/loongarch/vec_helper.c

@@ -12,6 +12,7 @@
 #include "fpu/softfloat.h"
 #include "internals.h"
 #include "tcg/tcg.h"
+#include "vec.h"
 
 #define DO_ADD(a, b)  (a + b)
 #define DO_SUB(a, b)  (a - b)