* [PATCH v4 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter
2025-03-10 2:35 [PATCH v4 0/2] Enhanced VSTART and VL checks for vector instructions Chao Liu
@ 2025-03-10 2:35 ` Chao Liu
2025-03-10 2:35 ` [PATCH v4 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction Chao Liu
2025-03-10 22:52 ` [PATCH v4 0/2] Enhanced VSTART and VL checks for vector instructions Alistair Francis
2 siblings, 0 replies; 6+ messages in thread
From: Chao Liu @ 2025-03-10 2:35 UTC (permalink / raw)
To: alistair23
Cc: alistair.francis, bmeng.cn, dbarboza, lc00631, liwei1518, palmer,
qemu-devel, qemu-riscv, zhiwei_liu, zqz00548
Some vector instructions are special, such as the vlm.v instruction,
where setting its vl actually sets evl = (vl + 7) >> 3. To improve
maintainability, we will uniformly use VSTART_CHECK_EARLY_EXIT() to
check for the condition vstart >= vl. This function will also handle
cases involving evl.
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>
---
target/riscv/vcrypto_helper.c | 32 +++++++--------
target/riscv/vector_helper.c | 69 ++++++++++++++++-----------------
target/riscv/vector_internals.c | 4 +-
target/riscv/vector_internals.h | 12 +++---
4 files changed, 57 insertions(+), 60 deletions(-)
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index f7423df..1526de9 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -222,7 +222,7 @@ static inline void xor_round_key(AESState *round_state, AESState *round_key)
uint32_t total_elems = vext_get_total_elems(env, desc, 4); \
uint32_t vta = vext_vta(desc); \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \
AESState round_key; \
@@ -248,7 +248,7 @@ static inline void xor_round_key(AESState *round_state, AESState *round_key)
uint32_t total_elems = vext_get_total_elems(env, desc, 4); \
uint32_t vta = vext_vta(desc); \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \
AESState round_key; \
@@ -309,7 +309,7 @@ void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
uimm &= 0b1111;
if (uimm > 10 || uimm == 0) {
@@ -357,7 +357,7 @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
uimm &= 0b1111;
if (uimm > 14 || uimm < 2) {
@@ -465,7 +465,7 @@ void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
if (sew == MO_32) {
@@ -582,7 +582,7 @@ void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
@@ -602,7 +602,7 @@ void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
@@ -622,7 +622,7 @@ void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
@@ -642,7 +642,7 @@ void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
@@ -676,7 +676,7 @@ void HELPER(vsm3me_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr,
uint32_t *vs1 = vs1_vptr;
uint32_t *vs2 = vs2_vptr;
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (int i = env->vstart / 8; i < env->vl / 8; i++) {
uint32_t w[24];
@@ -777,7 +777,7 @@ void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
uint32_t *vs2 = vs2_vptr;
uint32_t v1[8], v2[8], v3[8];
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (int i = env->vstart / 8; i < env->vl / 8; i++) {
for (int k = 0; k < 8; k++) {
@@ -802,7 +802,7 @@ void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr,
uint32_t vta = vext_vta(desc);
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]};
@@ -841,7 +841,7 @@ void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env,
uint32_t vta = vext_vta(desc);
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])};
@@ -879,7 +879,7 @@ void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uimm5, CPURISCVState *env,
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
@@ -937,7 +937,7 @@ void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
@@ -973,7 +973,7 @@ void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 71b823d..217d2f6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -260,7 +260,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, target_ulong stride,
uint32_t esz = 1 << log2_esz;
uint32_t vma = vext_vma(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
for (i = env->vstart; i < env->vl; env->vstart = ++i) {
k = 0;
@@ -383,10 +383,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
uint32_t msize = nf * esz;
int mmu_index = riscv_env_mmu_index(env, false);
- if (env->vstart >= evl) {
- env->vstart = 0;
- return;
- }
+ VSTART_CHECK_EARLY_EXIT(env, evl);
#if defined(CONFIG_USER_ONLY)
/*
@@ -544,7 +541,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
uint32_t esz = 1 << log2_esz;
uint32_t vma = vext_vma(desc);
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
/* load bytes from guest memory */
for (i = env->vstart; i < env->vl; env->vstart = ++i) {
@@ -638,7 +635,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, CPURISCVState *env,
int flags;
void *host;
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, env->vl);
addr = base + ((env->vstart * nf) << log2_esz);
page_split = -(addr | TARGET_PAGE_MASK);
@@ -1116,7 +1113,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
@@ -1150,7 +1147,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -1187,7 +1184,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
@@ -1227,7 +1224,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -1325,7 +1322,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -1374,7 +1371,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -1438,7 +1435,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
@@ -1505,7 +1502,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -2054,7 +2051,7 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
@@ -2080,7 +2077,7 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
@@ -2105,7 +2102,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \
@@ -2131,7 +2128,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -2178,7 +2175,7 @@ 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);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -2305,7 +2302,7 @@ 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);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -3104,7 +3101,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -3149,7 +3146,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -3737,7 +3734,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
if (vl == 0) { \
return; \
@@ -4260,7 +4257,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
@@ -4302,7 +4299,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -4497,7 +4494,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -4827,7 +4824,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t i; \
int a, b; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
a = vext_elem_mask(vs1, i); \
@@ -5022,7 +5019,7 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
uint32_t vma = vext_vma(desc); \
int i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -5059,7 +5056,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
target_ulong offset = s1, i_min, i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
i_min = MAX(env->vstart, offset); \
for (i = i_min; i < vl; i++) { \
@@ -5094,7 +5091,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
target_ulong i_max, i_min, i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
i_min = MIN(s1 < vlmax ? vlmax - s1 : 0, vl); \
i_max = MAX(i_min, env->vstart); \
@@ -5138,7 +5135,7 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -5189,7 +5186,7 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -5266,7 +5263,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint64_t index; \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -5311,7 +5308,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint64_t index = s1; \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -5407,7 +5404,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
index 05b2d01..b490b1d 100644
--- a/target/riscv/vector_internals.c
+++ b/target/riscv/vector_internals.c
@@ -66,7 +66,7 @@ void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
uint32_t vma = vext_vma(desc);
uint32_t i;
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -92,7 +92,7 @@ void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
uint32_t vma = vext_vma(desc);
uint32_t i;
- VSTART_CHECK_EARLY_EXIT(env);
+ VSTART_CHECK_EARLY_EXIT(env, vl);
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index a11cc83..8eee7e5 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -25,11 +25,11 @@
#include "tcg/tcg-gvec-desc.h"
#include "internals.h"
-#define VSTART_CHECK_EARLY_EXIT(env) do { \
- if (env->vstart >= env->vl) { \
- env->vstart = 0; \
- return; \
- } \
+#define VSTART_CHECK_EARLY_EXIT(env, vl) do { \
+ if (env->vstart >= vl) { \
+ env->vstart = 0; \
+ return; \
+ } \
} while (0)
static inline uint32_t vext_nf(uint32_t desc)
@@ -159,7 +159,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
- VSTART_CHECK_EARLY_EXIT(env); \
+ VSTART_CHECK_EARLY_EXIT(env, vl); \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
--
2.48.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v4 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction
2025-03-10 2:35 [PATCH v4 0/2] Enhanced VSTART and VL checks for vector instructions Chao Liu
2025-03-10 2:35 ` [PATCH v4 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter Chao Liu
@ 2025-03-10 2:35 ` Chao Liu
2025-03-24 4:48 ` Michael Tokarev
2025-03-10 22:52 ` [PATCH v4 0/2] Enhanced VSTART and VL checks for vector instructions Alistair Francis
2 siblings, 1 reply; 6+ messages in thread
From: Chao Liu @ 2025-03-10 2:35 UTC (permalink / raw)
To: alistair23
Cc: alistair.francis, bmeng.cn, dbarboza, lc00631, liwei1518, palmer,
qemu-devel, qemu-riscv, zhiwei_liu, zqz00548
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>
---
target/riscv/vector_helper.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 217d2f6..67b3baf 100644
--- a/target/riscv/vector_helper.c
+++ b/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; \
--
2.48.1
^ permalink raw reply related [flat|nested] 6+ messages in thread