target/riscv: fix handling of nop for vstart >= vl in some vector instruction

Recently, when I was writing a RISCV test, I found that when VL is set to 0, the
instruction should be nop, but when I tested it, I found that QEMU will treat
all elements as tail elements, and in the case of VTA=1, write all elements
to 1.

After troubleshooting, it was found that the vext_vx_rm_1 function was called in
the vext_vx_rm_2, and then the vext_set_elems_1s function was called to process
the tail element, but only VSTART >= vl was checked in the vext_vx_rm_1
function, which caused the tail element to still be processed even if it was
returned in advance.

So I've made the following change:

Put VSTART_CHECK_EARLY_EXIT(env) at the beginning of the vext_vx_rm_2 function,
so that the VSTART register is checked correctly.

Fixes: df4252b2ec ("target/riscv/vector_helpers: do early exit when
vstart >= vl")
Signed-off-by: Chao Liu <lc00631@tecorigin.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <b2649f14915150be4c602d63cd3ea4adf47e9d75.1741573286.git.lc00631@tecorigin.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

target/riscv/vector_helper.c

@@ -2175,8 +2175,6 @@ vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
              uint32_t vl, uint32_t vm, int vxrm,
              opivv2_rm_fn *fn, uint32_t vma, uint32_t esz)
 {
-    VSTART_CHECK_EARLY_EXIT(env, vl);
-
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             /* set masked-off elements to 1s */
@@ -2200,6 +2198,8 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
     uint32_t vta = vext_vta(desc);
     uint32_t vma = vext_vma(desc);
 
+    VSTART_CHECK_EARLY_EXIT(env, vl);
+
     switch (env->vxrm) {
     case 0: /* rnu */
         vext_vv_rm_1(vd, v0, vs1, vs2,
@@ -2302,8 +2302,6 @@ vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
              uint32_t vl, uint32_t vm, int vxrm,
              opivx2_rm_fn *fn, uint32_t vma, uint32_t esz)
 {
-    VSTART_CHECK_EARLY_EXIT(env, vl);
-
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             /* set masked-off elements to 1s */
@@ -2327,6 +2325,8 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
     uint32_t vta = vext_vta(desc);
     uint32_t vma = vext_vma(desc);
 
+    VSTART_CHECK_EARLY_EXIT(env, vl);
+
     switch (env->vxrm) {
     case 0: /* rnu */
         vext_vx_rm_1(vd, v0, s1, vs2,
@@ -4662,6 +4662,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
     uint32_t i;                                           \
     TD s1 =  *((TD *)vs1 + HD(0));                        \
                                                           \
+    VSTART_CHECK_EARLY_EXIT(env, vl);                     \
+                                                          \
     for (i = env->vstart; i < vl; i++) {                  \
         TS2 s2 = *((TS2 *)vs2 + HS2(i));                  \
         if (!vm && !vext_elem_mask(v0, i)) {              \
@@ -4750,6 +4752,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,           \
     uint32_t i;                                            \
     TD s1 =  *((TD *)vs1 + HD(0));                         \
                                                            \
+    VSTART_CHECK_EARLY_EXIT(env, vl);                      \
+                                                           \
     for (i = env->vstart; i < vl; i++) {                   \
         TS2 s2 = *((TS2 *)vs2 + HS2(i));                   \
         if (!vm && !vext_elem_mask(v0, i)) {               \
@@ -4914,6 +4918,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
     int i;
     bool first_mask_bit = false;
 
+    VSTART_CHECK_EARLY_EXIT(env, vl);
+
     for (i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             /* set masked-off elements to 1s */
@@ -4986,6 +4992,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env,      \
     uint32_t sum = 0;                                                     \
     int i;                                                                \
                                                                           \
+    VSTART_CHECK_EARLY_EXIT(env, vl);                                     \
+                                                                          \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
             /* set masked-off elements to 1s */                           \
@@ -5344,6 +5352,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,               \
     uint32_t vta = vext_vta(desc);                                        \
     uint32_t num = 0, i;                                                  \
                                                                           \
+    VSTART_CHECK_EARLY_EXIT(env, vl);                                     \
+                                                                          \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vext_elem_mask(vs1, i)) {                                    \
             continue;                                                     \