Merge tag 'qemu-sparc-20240506' of https://github.com/mcayland/qemu into staging

qemu-sparc queue

# -----BEGIN PGP SIGNATURE-----
#
# iQFSBAABCgA8FiEEzGIauY6CIA2RXMnEW8LFb64PMh8FAmY4wZceHG1hcmsuY2F2
# ZS1heWxhbmRAaWxhbmRlLmNvLnVrAAoJEFvCxW+uDzIftQsH+wfIWymTdQMowfM6
# Ze/T8KODn+MqU5eg25VPSTojnmr7LFaCj2yK6zWX61RwIqtMc3NaxX0G7ksW12/g
# 35ACqiEEd5WRDhAtVhj5Wp+WEDoR4AD3LWIaN7a/qjO3qb78l7Bujw3qXzGSq4lQ
# hST6dTgMwn5LhJOyz+5dORVUK1UZSBuDxHeKRHgdoFi6yqGQ5bao5TpaDYOnGSbx
# 8KPrAFfXG1T6xRS8Ih5HXAPE5VJztLFPiVtCTTrETDP/o8EzvOZj5y/nJVZXXC3N
# 57g+QyJX9EdrRZvobef4LnNnoZyiqG+uQNugglqZqjiiLjl6AzYxI+ed0hU+cZR9
# pz76Hr8=
# =i2cV
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 06 May 2024 04:40:07 AM PDT
# gpg:                using RSA key CC621AB98E82200D915CC9C45BC2C56FAE0F321F
# gpg:                issuer "mark.cave-ayland@ilande.co.uk"
# gpg: Good signature from "Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>" [full]

* tag 'qemu-sparc-20240506' of https://github.com/mcayland/qemu:
  target/sparc: Split out do_ms16b
  target/sparc: Fix FPMERGE
  target/sparc: Fix FMULD8*X16
  target/sparc: Fix FMUL8x16A{U,L}
  target/sparc: Fix FMUL8x16
  target/sparc: Fix FEXPAND
  linux-user/sparc: Add more hwcap bits for sparc64
  hw/sparc64: set iommu_platform=on for virtio devices attached to the sun4u machine
  docs/about: Deprecate the old "UltraSparc" CPU names that contain a "+"
  docs/system/target-sparc: Improve the Sparc documentation
  target/sparc/cpu: Avoid spaces by default in the CPU names
  target/sparc/cpu: Rename the CPU models with a "+" in their names

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

5 files changed, 208 insertions, 189 deletions

diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c
index 685485c654..5be1592e66 100644
--- a/target/sparc/cpu.c
+++ b/target/sparc/cpu.c
@@ -206,7 +206,7 @@ void cpu_sparc_set_id(CPUSPARCState *env, unsigned int cpu)
 static const sparc_def_t sparc_defs[] = {
 #ifdef TARGET_SPARC64
     {
-        .name = "Fujitsu Sparc64",
+        .name = "Fujitsu-Sparc64",
         .iu_version = ((0x04ULL << 48) | (0x02ULL << 32) | (0ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -215,7 +215,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Fujitsu Sparc64 III",
+        .name = "Fujitsu-Sparc64-III",
         .iu_version = ((0x04ULL << 48) | (0x03ULL << 32) | (0ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -224,7 +224,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Fujitsu Sparc64 IV",
+        .name = "Fujitsu-Sparc64-IV",
         .iu_version = ((0x04ULL << 48) | (0x04ULL << 32) | (0ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -233,7 +233,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Fujitsu Sparc64 V",
+        .name = "Fujitsu-Sparc64-V",
         .iu_version = ((0x04ULL << 48) | (0x05ULL << 32) | (0x51ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -242,7 +242,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI UltraSparc I",
+        .name = "TI-UltraSparc-I",
         .iu_version = ((0x17ULL << 48) | (0x10ULL << 32) | (0x40ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -251,7 +251,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI UltraSparc II",
+        .name = "TI-UltraSparc-II",
         .iu_version = ((0x17ULL << 48) | (0x11ULL << 32) | (0x20ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -260,7 +260,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI UltraSparc IIi",
+        .name = "TI-UltraSparc-IIi",
         .iu_version = ((0x17ULL << 48) | (0x12ULL << 32) | (0x91ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -269,7 +269,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI UltraSparc IIe",
+        .name = "TI-UltraSparc-IIe",
         .iu_version = ((0x17ULL << 48) | (0x13ULL << 32) | (0x14ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -278,7 +278,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc III",
+        .name = "Sun-UltraSparc-III",
         .iu_version = ((0x3eULL << 48) | (0x14ULL << 32) | (0x34ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -287,7 +287,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc III Cu",
+        .name = "Sun-UltraSparc-III-Cu",
         .iu_version = ((0x3eULL << 48) | (0x15ULL << 32) | (0x41ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_3,
@@ -296,7 +296,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc IIIi",
+        .name = "Sun-UltraSparc-IIIi",
         .iu_version = ((0x3eULL << 48) | (0x16ULL << 32) | (0x34ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -305,7 +305,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc IV",
+        .name = "Sun-UltraSparc-IV",
         .iu_version = ((0x3eULL << 48) | (0x18ULL << 32) | (0x31ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_4,
@@ -314,7 +314,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc IV+",
+        .name = "Sun-UltraSparc-IV-plus",
         .iu_version = ((0x3eULL << 48) | (0x19ULL << 32) | (0x22ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -323,7 +323,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES | CPU_FEATURE_CMT,
     },
     {
-        .name = "Sun UltraSparc IIIi+",
+        .name = "Sun-UltraSparc-IIIi-plus",
         .iu_version = ((0x3eULL << 48) | (0x22ULL << 32) | (0ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_3,
@@ -332,7 +332,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Sun UltraSparc T1",
+        .name = "Sun-UltraSparc-T1",
         /* defined in sparc_ifu_fdp.v and ctu.h */
         .iu_version = ((0x3eULL << 48) | (0x23ULL << 32) | (0x02ULL << 24)),
         .fpu_version = 0x00000000,
@@ -343,7 +343,7 @@ static const sparc_def_t sparc_defs[] = {
         | CPU_FEATURE_GL,
     },
     {
-        .name = "Sun UltraSparc T2",
+        .name = "Sun-UltraSparc-T2",
         /* defined in tlu_asi_ctl.v and n2_revid_cust.v */
         .iu_version = ((0x3eULL << 48) | (0x24ULL << 32) | (0x02ULL << 24)),
         .fpu_version = 0x00000000,
@@ -354,7 +354,7 @@ static const sparc_def_t sparc_defs[] = {
         | CPU_FEATURE_GL,
     },
     {
-        .name = "NEC UltraSparc I",
+        .name = "NEC-UltraSparc-I",
         .iu_version = ((0x22ULL << 48) | (0x10ULL << 32) | (0x40ULL << 24)),
         .fpu_version = 0x00000000,
         .mmu_version = mmu_us_12,
@@ -364,7 +364,7 @@ static const sparc_def_t sparc_defs[] = {
     },
 #else
     {
-        .name = "Fujitsu MB86904",
+        .name = "Fujitsu-MB86904",
         .iu_version = 0x04 << 24, /* Impl 0, ver 4 */
         .fpu_version = 4 << FSR_VER_SHIFT, /* FPU version 4 (Meiko) */
         .mmu_version = 0x04 << 24, /* Impl 0, ver 4 */
@@ -377,7 +377,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "Fujitsu MB86907",
+        .name = "Fujitsu-MB86907",
         .iu_version = 0x05 << 24, /* Impl 0, ver 5 */
         .fpu_version = 4 << FSR_VER_SHIFT, /* FPU version 4 (Meiko) */
         .mmu_version = 0x05 << 24, /* Impl 0, ver 5 */
@@ -390,7 +390,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI MicroSparc I",
+        .name = "TI-MicroSparc-I",
         .iu_version = 0x41000000,
         .fpu_version = 4 << FSR_VER_SHIFT,
         .mmu_version = 0x41000000,
@@ -403,7 +403,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_FEATURE_MUL | CPU_FEATURE_DIV,
     },
     {
-        .name = "TI MicroSparc II",
+        .name = "TI-MicroSparc-II",
         .iu_version = 0x42000000,
         .fpu_version = 4 << FSR_VER_SHIFT,
         .mmu_version = 0x02000000,
@@ -416,7 +416,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI MicroSparc IIep",
+        .name = "TI-MicroSparc-IIep",
         .iu_version = 0x42000000,
         .fpu_version = 4 << FSR_VER_SHIFT,
         .mmu_version = 0x04000000,
@@ -429,7 +429,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc 40", /* STP1020NPGA */
+        .name = "TI-SuperSparc-40", /* STP1020NPGA */
         .iu_version = 0x41000000, /* SuperSPARC 2.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x00000800, /* SuperSPARC 2.x, no MXCC */
@@ -442,7 +442,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc 50", /* STP1020PGA */
+        .name = "TI-SuperSparc-50", /* STP1020PGA */
         .iu_version = 0x40000000, /* SuperSPARC 3.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x01000800, /* SuperSPARC 3.x, no MXCC */
@@ -455,7 +455,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc 51",
+        .name = "TI-SuperSparc-51",
         .iu_version = 0x40000000, /* SuperSPARC 3.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x01000000, /* SuperSPARC 3.x, MXCC */
@@ -469,7 +469,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc 60", /* STP1020APGA */
+        .name = "TI-SuperSparc-60", /* STP1020APGA */
         .iu_version = 0x40000000, /* SuperSPARC 3.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x01000800, /* SuperSPARC 3.x, no MXCC */
@@ -482,7 +482,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc 61",
+        .name = "TI-SuperSparc-61",
         .iu_version = 0x44000000, /* SuperSPARC 3.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x01000000, /* SuperSPARC 3.x, MXCC */
@@ -496,7 +496,7 @@ static const sparc_def_t sparc_defs[] = {
         .features = CPU_DEFAULT_FEATURES,
     },
     {
-        .name = "TI SuperSparc II",
+        .name = "TI-SuperSparc-II",
         .iu_version = 0x40000000, /* SuperSPARC II 1.x */
         .fpu_version = 0 << FSR_VER_SHIFT,
         .mmu_version = 0x08000000, /* SuperSPARC II 1.x, MXCC */
@@ -762,6 +762,16 @@ static ObjectClass *sparc_cpu_class_by_name(const char *cpu_model)
     char *typename;
 
     typename = sparc_cpu_type_name(cpu_model);
+
+    /* Fix up legacy names with '+' in it */
+    if (g_str_equal(typename, SPARC_CPU_TYPE_NAME("Sun-UltraSparc-IV+"))) {
+        g_free(typename);
+        typename = g_strdup(SPARC_CPU_TYPE_NAME("Sun-UltraSparc-IV-plus"));
+    } else if (g_str_equal(typename, SPARC_CPU_TYPE_NAME("Sun-UltraSparc-IIIi+"))) {
+        g_free(typename);
+        typename = g_strdup(SPARC_CPU_TYPE_NAME("Sun-UltraSparc-IIIi-plus"));
+    }
+
     oc = object_class_by_name(typename);
     g_free(typename);
     return oc;
diff --git a/target/sparc/helper.h b/target/sparc/helper.h
index b8087d0d2b..97fbf6f66c 100644
--- a/target/sparc/helper.h
+++ b/target/sparc/helper.h
@@ -94,15 +94,12 @@ DEF_HELPER_FLAGS_2(fstox, TCG_CALL_NO_WG, s64, env, f32)
 DEF_HELPER_FLAGS_2(fdtox, TCG_CALL_NO_WG, s64, env, f64)
 DEF_HELPER_FLAGS_2(fqtox, TCG_CALL_NO_WG, s64, env, i128)
 
-DEF_HELPER_FLAGS_2(fpmerge, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmul8x16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmul8x16al, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmul8x16au, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(fpmerge, TCG_CALL_NO_RWG_SE, i64, i32, i32)
+DEF_HELPER_FLAGS_2(fmul8x16, TCG_CALL_NO_RWG_SE, i64, i32, i64)
+DEF_HELPER_FLAGS_2(fmul8x16a, TCG_CALL_NO_RWG_SE, i64, i32, s32)
 DEF_HELPER_FLAGS_2(fmul8sux16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(fmul8ulx16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmuld8sux16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmuld8ulx16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fexpand, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_1(fexpand, TCG_CALL_NO_RWG_SE, i64, i32)
 DEF_HELPER_FLAGS_3(pdist, TCG_CALL_NO_RWG_SE, i64, i64, i64, i64)
 DEF_HELPER_FLAGS_2(fpack16, TCG_CALL_NO_RWG_SE, i32, i64, i64)
 DEF_HELPER_FLAGS_3(fpack32, TCG_CALL_NO_RWG_SE, i64, i64, i64, i64)
diff --git a/target/sparc/insns.decode b/target/sparc/insns.decode
index 2d26404cb2..e2d8a07dc4 100644
--- a/target/sparc/insns.decode
+++ b/target/sparc/insns.decode
@@ -352,7 +352,7 @@ FCMPEq      10 000 cc:2 110101 rs1:5  0 0101 0111 rs2:5
     FALIGNDATAg 10 ..... 110110 ..... 0 0100 1000 .....    @r_r_r
     FPMERGE     10 ..... 110110 ..... 0 0100 1011 .....    @r_r_r
     BSHUFFLE    10 ..... 110110 ..... 0 0100 1100 .....    @r_r_r
-    FEXPAND     10 ..... 110110 ..... 0 0100 1101 .....    @r_r_r
+    FEXPAND     10 ..... 110110 00000 0 0100 1101 .....    @r_r2
 
     FSRCd       10 ..... 110110 ..... 0 0111 0100 00000    @r_r1  # FSRC1d
     FSRCs       10 ..... 110110 ..... 0 0111 0101 00000    @r_r1  # FSRC1s
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index 571b3e3f03..99c6f3cc72 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -45,6 +45,7 @@
 # define gen_helper_clear_softint(E, S)         qemu_build_not_reached()
 # define gen_helper_done(E)                     qemu_build_not_reached()
 # define gen_helper_flushw(E)                   qemu_build_not_reached()
+# define gen_helper_fmul8x16a(D, S1, S2)        qemu_build_not_reached()
 # define gen_helper_rdccr(D, E)                 qemu_build_not_reached()
 # define gen_helper_rdcwp(D, E)                 qemu_build_not_reached()
 # define gen_helper_restored(E)                 qemu_build_not_reached()
@@ -72,11 +73,7 @@
 # define gen_helper_fexpand              ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fmul8sux16           ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fmul8ulx16           ({ qemu_build_not_reached(); NULL; })
-# define gen_helper_fmul8x16al           ({ qemu_build_not_reached(); NULL; })
-# define gen_helper_fmul8x16au           ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fmul8x16             ({ qemu_build_not_reached(); NULL; })
-# define gen_helper_fmuld8sux16          ({ qemu_build_not_reached(); NULL; })
-# define gen_helper_fmuld8ulx16          ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fpmerge              ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fqtox                ({ qemu_build_not_reached(); NULL; })
 # define gen_helper_fstox                ({ qemu_build_not_reached(); NULL; })
@@ -719,6 +716,60 @@ static void gen_op_bshuffle(TCGv_i64 dst, TCGv_i64 src1, TCGv_i64 src2)
 #endif
 }
 
+static void gen_op_fmul8x16al(TCGv_i64 dst, TCGv_i32 src1, TCGv_i32 src2)
+{
+    tcg_gen_ext16s_i32(src2, src2);
+    gen_helper_fmul8x16a(dst, src1, src2);
+}
+
+static void gen_op_fmul8x16au(TCGv_i64 dst, TCGv_i32 src1, TCGv_i32 src2)
+{
+    tcg_gen_sari_i32(src2, src2, 16);
+    gen_helper_fmul8x16a(dst, src1, src2);
+}
+
+static void gen_op_fmuld8ulx16(TCGv_i64 dst, TCGv_i32 src1, TCGv_i32 src2)
+{
+    TCGv_i32 t0 = tcg_temp_new_i32();
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    tcg_gen_ext8u_i32(t0, src1);
+    tcg_gen_ext16s_i32(t1, src2);
+    tcg_gen_mul_i32(t0, t0, t1);
+
+    tcg_gen_extract_i32(t1, src1, 16, 8);
+    tcg_gen_sextract_i32(t2, src2, 16, 16);
+    tcg_gen_mul_i32(t1, t1, t2);
+
+    tcg_gen_concat_i32_i64(dst, t0, t1);
+}
+
+static void gen_op_fmuld8sux16(TCGv_i64 dst, TCGv_i32 src1, TCGv_i32 src2)
+{
+    TCGv_i32 t0 = tcg_temp_new_i32();
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    /*
+     * The insn description talks about extracting the upper 8 bits
+     * of the signed 16-bit input rs1, performing the multiply, then
+     * shifting left by 8 bits.  Instead, zap the lower 8 bits of
+     * the rs1 input, which avoids the need for two shifts.
+     */
+    tcg_gen_ext16s_i32(t0, src1);
+    tcg_gen_andi_i32(t0, t0, ~0xff);
+    tcg_gen_ext16s_i32(t1, src2);
+    tcg_gen_mul_i32(t0, t0, t1);
+
+    tcg_gen_sextract_i32(t1, src1, 16, 16);
+    tcg_gen_andi_i32(t1, t1, ~0xff);
+    tcg_gen_sextract_i32(t2, src2, 16, 16);
+    tcg_gen_mul_i32(t1, t1, t2);
+
+    tcg_gen_concat_i32_i64(dst, t0, t1);
+}
+
 static void finishing_insn(DisasContext *dc)
 {
     /*
@@ -4358,6 +4409,25 @@ TRANS(FSQRTd, ALL, do_env_dd, a, gen_helper_fsqrtd)
 TRANS(FxTOd, 64, do_env_dd, a, gen_helper_fxtod)
 TRANS(FdTOx, 64, do_env_dd, a, gen_helper_fdtox)
 
+static bool do_df(DisasContext *dc, arg_r_r *a,
+                  void (*func)(TCGv_i64, TCGv_i32))
+{
+    TCGv_i64 dst;
+    TCGv_i32 src;
+
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+
+    dst = tcg_temp_new_i64();
+    src = gen_load_fpr_F(dc, a->rs);
+    func(dst, src);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
+TRANS(FEXPAND, VIS1, do_df, a, gen_helper_fexpand)
+
 static bool do_env_df(DisasContext *dc, arg_r_r *a,
                       void (*func)(TCGv_i64, TCGv_env, TCGv_i32))
 {
@@ -4564,6 +4634,50 @@ TRANS(FSUBs, ALL, do_env_fff, a, gen_helper_fsubs)
 TRANS(FMULs, ALL, do_env_fff, a, gen_helper_fmuls)
 TRANS(FDIVs, ALL, do_env_fff, a, gen_helper_fdivs)
 
+static bool do_dff(DisasContext *dc, arg_r_r_r *a,
+                   void (*func)(TCGv_i64, TCGv_i32, TCGv_i32))
+{
+    TCGv_i64 dst;
+    TCGv_i32 src1, src2;
+
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+
+    dst = gen_dest_fpr_D(dc, a->rd);
+    src1 = gen_load_fpr_F(dc, a->rs1);
+    src2 = gen_load_fpr_F(dc, a->rs2);
+    func(dst, src1, src2);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
+TRANS(FMUL8x16AU, VIS1, do_dff, a, gen_op_fmul8x16au)
+TRANS(FMUL8x16AL, VIS1, do_dff, a, gen_op_fmul8x16al)
+TRANS(FMULD8SUx16, VIS1, do_dff, a, gen_op_fmuld8sux16)
+TRANS(FMULD8ULx16, VIS1, do_dff, a, gen_op_fmuld8ulx16)
+TRANS(FPMERGE, VIS1, do_dff, a, gen_helper_fpmerge)
+
+static bool do_dfd(DisasContext *dc, arg_r_r_r *a,
+                   void (*func)(TCGv_i64, TCGv_i32, TCGv_i64))
+{
+    TCGv_i64 dst, src2;
+    TCGv_i32 src1;
+
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+
+    dst = gen_dest_fpr_D(dc, a->rd);
+    src1 = gen_load_fpr_F(dc, a->rs1);
+    src2 = gen_load_fpr_D(dc, a->rs2);
+    func(dst, src1, src2);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
+TRANS(FMUL8x16, VIS1, do_dfd, a, gen_helper_fmul8x16)
+
 static bool do_ddd(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv_i64, TCGv_i64, TCGv_i64))
 {
@@ -4581,15 +4695,8 @@ static bool do_ddd(DisasContext *dc, arg_r_r_r *a,
     return advance_pc(dc);
 }
 
-TRANS(FMUL8x16, VIS1, do_ddd, a, gen_helper_fmul8x16)
-TRANS(FMUL8x16AU, VIS1, do_ddd, a, gen_helper_fmul8x16au)
-TRANS(FMUL8x16AL, VIS1, do_ddd, a, gen_helper_fmul8x16al)
 TRANS(FMUL8SUx16, VIS1, do_ddd, a, gen_helper_fmul8sux16)
 TRANS(FMUL8ULx16, VIS1, do_ddd, a, gen_helper_fmul8ulx16)
-TRANS(FMULD8SUx16, VIS1, do_ddd, a, gen_helper_fmuld8sux16)
-TRANS(FMULD8ULx16, VIS1, do_ddd, a, gen_helper_fmuld8ulx16)
-TRANS(FPMERGE, VIS1, do_ddd, a, gen_helper_fpmerge)
-TRANS(FEXPAND, VIS1, do_ddd, a, gen_helper_fexpand)
 
 TRANS(FPADD16, VIS1, do_ddd, a, tcg_gen_vec_add16_i64)
 TRANS(FPADD32, VIS1, do_ddd, a, tcg_gen_vec_add32_i64)
diff --git a/target/sparc/vis_helper.c b/target/sparc/vis_helper.c
index 7763b16c24..e15c6bb34e 100644
--- a/target/sparc/vis_helper.c
+++ b/target/sparc/vis_helper.c
@@ -44,6 +44,7 @@ target_ulong helper_array8(target_ulong pixel_addr, target_ulong cubesize)
 
 #if HOST_BIG_ENDIAN
 #define VIS_B64(n) b[7 - (n)]
+#define VIS_SB64(n) sb[7 - (n)]
 #define VIS_W64(n) w[3 - (n)]
 #define VIS_SW64(n) sw[3 - (n)]
 #define VIS_L64(n) l[1 - (n)]
@@ -51,6 +52,7 @@ target_ulong helper_array8(target_ulong pixel_addr, target_ulong cubesize)
 #define VIS_W32(n) w[1 - (n)]
 #else
 #define VIS_B64(n) b[n]
+#define VIS_SB64(n) sb[n]
 #define VIS_W64(n) w[n]
 #define VIS_SW64(n) sw[n]
 #define VIS_L64(n) l[n]
@@ -60,6 +62,7 @@ target_ulong helper_array8(target_ulong pixel_addr, target_ulong cubesize)
 
 typedef union {
     uint8_t b[8];
+    int8_t sb[8];
     uint16_t w[4];
     int16_t sw[4];
     uint32_t l[2];
@@ -74,94 +77,60 @@ typedef union {
     float32 f;
 } VIS32;
 
-uint64_t helper_fpmerge(uint64_t src1, uint64_t src2)
+uint64_t helper_fpmerge(uint32_t src1, uint32_t src2)
 {
-    VIS64 s, d;
+    VIS32 s1, s2;
+    VIS64 d;
 
-    s.ll = src1;
-    d.ll = src2;
+    s1.l = src1;
+    s2.l = src2;
+    d.ll = 0;
 
-    /* Reverse calculation order to handle overlap */
-    d.VIS_B64(7) = s.VIS_B64(3);
-    d.VIS_B64(6) = d.VIS_B64(3);
-    d.VIS_B64(5) = s.VIS_B64(2);
-    d.VIS_B64(4) = d.VIS_B64(2);
-    d.VIS_B64(3) = s.VIS_B64(1);
-    d.VIS_B64(2) = d.VIS_B64(1);
-    d.VIS_B64(1) = s.VIS_B64(0);
-    /* d.VIS_B64(0) = d.VIS_B64(0); */
+    d.VIS_B64(7) = s1.VIS_B32(3);
+    d.VIS_B64(6) = s2.VIS_B32(3);
+    d.VIS_B64(5) = s1.VIS_B32(2);
+    d.VIS_B64(4) = s2.VIS_B32(2);
+    d.VIS_B64(3) = s1.VIS_B32(1);
+    d.VIS_B64(2) = s2.VIS_B32(1);
+    d.VIS_B64(1) = s1.VIS_B32(0);
+    d.VIS_B64(0) = s2.VIS_B32(0);
 
     return d.ll;
 }
 
-uint64_t helper_fmul8x16(uint64_t src1, uint64_t src2)
+static inline int do_ms16b(int x, int y)
 {
-    VIS64 s, d;
-    uint32_t tmp;
-
-    s.ll = src1;
-    d.ll = src2;
-
-#define PMUL(r)                                                 \
-    tmp = (int32_t)d.VIS_SW64(r) * (int32_t)s.VIS_B64(r);       \
-    if ((tmp & 0xff) > 0x7f) {                                  \
-        tmp += 0x100;                                           \
-    }                                                           \
-    d.VIS_W64(r) = tmp >> 8;
-
-    PMUL(0);
-    PMUL(1);
-    PMUL(2);
-    PMUL(3);
-#undef PMUL
-
-    return d.ll;
+    return ((x * y) + 0x80) >> 8;
 }
 
-uint64_t helper_fmul8x16al(uint64_t src1, uint64_t src2)
+uint64_t helper_fmul8x16(uint32_t src1, uint64_t src2)
 {
-    VIS64 s, d;
-    uint32_t tmp;
+    VIS64 d;
+    VIS32 s;
 
-    s.ll = src1;
+    s.l = src1;
     d.ll = src2;
 
-#define PMUL(r)                                                 \
-    tmp = (int32_t)d.VIS_SW64(1) * (int32_t)s.VIS_B64(r);       \
-    if ((tmp & 0xff) > 0x7f) {                                  \
-        tmp += 0x100;                                           \
-    }                                                           \
-    d.VIS_W64(r) = tmp >> 8;
-
-    PMUL(0);
-    PMUL(1);
-    PMUL(2);
-    PMUL(3);
-#undef PMUL
+    d.VIS_W64(0) = do_ms16b(s.VIS_B32(0), d.VIS_SW64(0));
+    d.VIS_W64(1) = do_ms16b(s.VIS_B32(1), d.VIS_SW64(1));
+    d.VIS_W64(2) = do_ms16b(s.VIS_B32(2), d.VIS_SW64(2));
+    d.VIS_W64(3) = do_ms16b(s.VIS_B32(3), d.VIS_SW64(3));
 
     return d.ll;
 }
 
-uint64_t helper_fmul8x16au(uint64_t src1, uint64_t src2)
+uint64_t helper_fmul8x16a(uint32_t src1, int32_t src2)
 {
-    VIS64 s, d;
-    uint32_t tmp;
-
-    s.ll = src1;
-    d.ll = src2;
+    VIS32 s;
+    VIS64 d;
 
-#define PMUL(r)                                                 \
-    tmp = (int32_t)d.VIS_SW64(0) * (int32_t)s.VIS_B64(r);       \
-    if ((tmp & 0xff) > 0x7f) {                                  \
-        tmp += 0x100;                                           \
-    }                                                           \
-    d.VIS_W64(r) = tmp >> 8;
+    s.l = src1;
+    d.ll = 0;
 
-    PMUL(0);
-    PMUL(1);
-    PMUL(2);
-    PMUL(3);
-#undef PMUL
+    d.VIS_W64(0) = do_ms16b(s.VIS_B32(0), src2);
+    d.VIS_W64(1) = do_ms16b(s.VIS_B32(1), src2);
+    d.VIS_W64(2) = do_ms16b(s.VIS_B32(2), src2);
+    d.VIS_W64(3) = do_ms16b(s.VIS_B32(3), src2);
 
     return d.ll;
 }
@@ -169,23 +138,14 @@ uint64_t helper_fmul8x16au(uint64_t src1, uint64_t src2)
 uint64_t helper_fmul8sux16(uint64_t src1, uint64_t src2)
 {
     VIS64 s, d;
-    uint32_t tmp;
 
     s.ll = src1;
     d.ll = src2;
 
-#define PMUL(r)                                                         \
-    tmp = (int32_t)d.VIS_SW64(r) * ((int32_t)s.VIS_SW64(r) >> 8);       \
-    if ((tmp & 0xff) > 0x7f) {                                          \
-        tmp += 0x100;                                                   \
-    }                                                                   \
-    d.VIS_W64(r) = tmp >> 8;
-
-    PMUL(0);
-    PMUL(1);
-    PMUL(2);
-    PMUL(3);
-#undef PMUL
+    d.VIS_W64(0) = do_ms16b(s.VIS_SB64(1), d.VIS_SW64(0));
+    d.VIS_W64(1) = do_ms16b(s.VIS_SB64(3), d.VIS_SW64(1));
+    d.VIS_W64(2) = do_ms16b(s.VIS_SB64(5), d.VIS_SW64(2));
+    d.VIS_W64(3) = do_ms16b(s.VIS_SB64(7), d.VIS_SW64(3));
 
     return d.ll;
 }
@@ -193,80 +153,25 @@ uint64_t helper_fmul8sux16(uint64_t src1, uint64_t src2)
 uint64_t helper_fmul8ulx16(uint64_t src1, uint64_t src2)
 {
     VIS64 s, d;
-    uint32_t tmp;
 
     s.ll = src1;
     d.ll = src2;
 
-#define PMUL(r)                                                         \
-    tmp = (int32_t)d.VIS_SW64(r) * ((uint32_t)s.VIS_B64(r * 2));        \
-    if ((tmp & 0xff) > 0x7f) {                                          \
-        tmp += 0x100;                                                   \
-    }                                                                   \
-    d.VIS_W64(r) = tmp >> 8;
-
-    PMUL(0);
-    PMUL(1);
-    PMUL(2);
-    PMUL(3);
-#undef PMUL
-
-    return d.ll;
-}
-
-uint64_t helper_fmuld8sux16(uint64_t src1, uint64_t src2)
-{
-    VIS64 s, d;
-    uint32_t tmp;
-
-    s.ll = src1;
-    d.ll = src2;
-
-#define PMUL(r)                                                         \
-    tmp = (int32_t)d.VIS_SW64(r) * ((int32_t)s.VIS_SW64(r) >> 8);       \
-    if ((tmp & 0xff) > 0x7f) {                                          \
-        tmp += 0x100;                                                   \
-    }                                                                   \
-    d.VIS_L64(r) = tmp;
-
-    /* Reverse calculation order to handle overlap */
-    PMUL(1);
-    PMUL(0);
-#undef PMUL
+    d.VIS_W64(0) = do_ms16b(s.VIS_B64(0), d.VIS_SW64(0));
+    d.VIS_W64(1) = do_ms16b(s.VIS_B64(2), d.VIS_SW64(1));
+    d.VIS_W64(2) = do_ms16b(s.VIS_B64(4), d.VIS_SW64(2));
+    d.VIS_W64(3) = do_ms16b(s.VIS_B64(6), d.VIS_SW64(3));
 
     return d.ll;
 }
 
-uint64_t helper_fmuld8ulx16(uint64_t src1, uint64_t src2)
-{
-    VIS64 s, d;
-    uint32_t tmp;
-
-    s.ll = src1;
-    d.ll = src2;
-
-#define PMUL(r)                                                         \
-    tmp = (int32_t)d.VIS_SW64(r) * ((uint32_t)s.VIS_B64(r * 2));        \
-    if ((tmp & 0xff) > 0x7f) {                                          \
-        tmp += 0x100;                                                   \
-    }                                                                   \
-    d.VIS_L64(r) = tmp;
-
-    /* Reverse calculation order to handle overlap */
-    PMUL(1);
-    PMUL(0);
-#undef PMUL
-
-    return d.ll;
-}
-
-uint64_t helper_fexpand(uint64_t src1, uint64_t src2)
+uint64_t helper_fexpand(uint32_t src2)
 {
     VIS32 s;
     VIS64 d;
 
-    s.l = (uint32_t)src1;
-    d.ll = src2;
+    s.l = src2;
+    d.ll = 0;
     d.VIS_W64(0) = s.VIS_B32(0) << 4;
     d.VIS_W64(1) = s.VIS_B32(1) << 4;
     d.VIS_W64(2) = s.VIS_B32(2) << 4;