diff --git a/docs/about/emulation.rst b/docs/about/emulation.rst
index 3bc3579434..a72591ee4d 100644
--- a/docs/about/emulation.rst
+++ b/docs/about/emulation.rst
@@ -171,7 +171,7 @@ for that architecture.
     - Unified Hosting Interface (MD01069)
   * - RISC-V
     - System and User-mode
-    - https://github.com/riscv/riscv-semihosting-spec/blob/main/riscv-semihosting-spec.adoc
+    - https://github.com/riscv-non-isa/riscv-semihosting/blob/main/riscv-semihosting.adoc
   * - Xtensa
     - System
     - Tensilica ISS SIMCALL
diff --git a/hw/riscv/riscv-iommu-bits.h b/hw/riscv/riscv-iommu-bits.h
index b7cb1bc736..1017d73fc6 100644
--- a/hw/riscv/riscv-iommu-bits.h
+++ b/hw/riscv/riscv-iommu-bits.h
@@ -415,12 +415,16 @@ enum riscv_iommu_fq_causes {
 #define RISCV_IOMMU_DC_MSIPTP_MODE_OFF  0
 #define RISCV_IOMMU_DC_MSIPTP_MODE_FLAT 1
 
+/* 2.2 Process Directory Table */
+#define RISCV_IOMMU_PDTE_VALID          BIT_ULL(0)
+#define RISCV_IOMMU_PDTE_PPN            RISCV_IOMMU_PPN_FIELD
+
 /* Translation attributes fields */
 #define RISCV_IOMMU_PC_TA_V             BIT_ULL(0)
 #define RISCV_IOMMU_PC_TA_RESERVED      GENMASK_ULL(63, 32)
 
 /* First stage context fields */
-#define RISCV_IOMMU_PC_FSC_PPN          GENMASK_ULL(43, 0)
+#define RISCV_IOMMU_PC_FSC_PPN          RISCV_IOMMU_ATP_PPN_FIELD
 #define RISCV_IOMMU_PC_FSC_RESERVED     GENMASK_ULL(59, 44)
 
 enum riscv_iommu_fq_ttypes {
diff --git a/hw/riscv/riscv-iommu.c b/hw/riscv/riscv-iommu.c
index d46beb2d64..76e0fcd873 100644
--- a/hw/riscv/riscv-iommu.c
+++ b/hw/riscv/riscv-iommu.c
@@ -1042,10 +1042,10 @@ static int riscv_iommu_ctx_fetch(RISCVIOMMUState *s, RISCVIOMMUContext *ctx)
             return RISCV_IOMMU_FQ_CAUSE_PDT_LOAD_FAULT;
         }
         le64_to_cpus(&de);
-        if (!(de & RISCV_IOMMU_PC_TA_V)) {
+        if (!(de & RISCV_IOMMU_PDTE_VALID)) {
             return RISCV_IOMMU_FQ_CAUSE_PDT_INVALID;
         }
-        addr = PPN_PHYS(get_field(de, RISCV_IOMMU_PC_FSC_PPN));
+        addr = PPN_PHYS(get_field(de, RISCV_IOMMU_PDTE_PPN));
     }
 
     riscv_iommu_hpm_incr_ctr(s, ctx, RISCV_IOMMU_HPMEVENT_PD_WALK);
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index b32de763f7..8bfe4912e1 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -9119,35 +9119,38 @@ static void risc_hwprobe_fill_pairs(CPURISCVState *env,
     }
 }
 
-static int cpu_set_valid(abi_long arg3, abi_long arg4)
+/*
+ * If the cpumask_t of (target_cpus, cpusetsize) cannot be read: -EFAULT.
+ * If the cpumast_t has no bits set: -EINVAL.
+ * Otherwise the cpumask_t contains some bit set: 0.
+ * Unlike the kernel, we do not mask cpumask_t by the set of online cpus,
+ * nor bound the search by cpumask_size().
+ */
+static int nonempty_cpu_set(abi_ulong cpusetsize, abi_ptr target_cpus)
 {
-    int ret, i, tmp;
-    size_t host_mask_size, target_mask_size;
-    unsigned long *host_mask;
+    unsigned char *p = lock_user(VERIFY_READ, target_cpus, cpusetsize, 1);
+    int ret = -TARGET_EFAULT;
 
-    /*
-     * cpu_set_t represent CPU masks as bit masks of type unsigned long *.
-     * arg3 contains the cpu count.
-     */
-    tmp = (8 * sizeof(abi_ulong));
-    target_mask_size = ((arg3 + tmp - 1) / tmp) * sizeof(abi_ulong);
-    host_mask_size = (target_mask_size + (sizeof(*host_mask) - 1)) &
-                     ~(sizeof(*host_mask) - 1);
-
-    host_mask = alloca(host_mask_size);
-
-    ret = target_to_host_cpu_mask(host_mask, host_mask_size,
-                                  arg4, target_mask_size);
-    if (ret != 0) {
-        return ret;
-    }
-
-    for (i = 0 ; i < host_mask_size / sizeof(*host_mask); i++) {
-        if (host_mask[i] != 0) {
-            return 0;
+    if (p) {
+        ret = -TARGET_EINVAL;
+        /*
+         * Since we only care about the empty/non-empty state of the cpumask_t
+         * not the individual bits, we do not need to repartition the bits
+         * from target abi_ulong to host unsigned long.
+         *
+         * Note that the kernel does not round up cpusetsize to a multiple of
+         * sizeof(abi_ulong).  After bounding cpusetsize by cpumask_size(),
+         * it copies exactly cpusetsize bytes into a zeroed buffer.
+         */
+        for (abi_ulong i = 0; i < cpusetsize; ++i) {
+            if (p[i]) {
+                ret = 0;
+                break;
+            }
         }
+        unlock_user(p, target_cpus, 0);
     }
-    return -TARGET_EINVAL;
+    return ret;
 }
 
 static abi_long do_riscv_hwprobe(CPUArchState *cpu_env, abi_long arg1,
@@ -9164,7 +9167,7 @@ static abi_long do_riscv_hwprobe(CPUArchState *cpu_env, abi_long arg1,
 
     /* check cpu_set */
     if (arg3 != 0) {
-        ret = cpu_set_valid(arg3, arg4);
+        ret = nonempty_cpu_set(arg3, arg4);
         if (ret != 0) {
             return ret;
         }
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 7de19b4183..51e49e03de 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -765,6 +765,18 @@ static inline RISCVMXL riscv_cpu_sxl(CPURISCVState *env)
 }
 #endif
 
+static inline bool riscv_cpu_allow_16bit_insn(const RISCVCPUConfig *cfg,
+                                              target_long priv_ver,
+                                              uint32_t misa_ext)
+{
+    /* In priv spec version 1.12 or newer, C always implies Zca */
+    if (priv_ver >= PRIV_VERSION_1_12_0) {
+        return cfg->ext_zca;
+    } else {
+        return misa_ext & RVC;
+    }
+}
+
 /*
  * Encode LMUL to lmul as follows:
  *     LMUL    vlmul    lmul
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index 49566d3c08..7948188356 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -192,6 +192,11 @@ static RISCVException cfi_ss(CPURISCVState *env, int csrno)
         return RISCV_EXCP_ILLEGAL_INST;
     }
 
+    /* If ext implemented, M-mode always have access to SSP CSR */
+    if (env->priv == PRV_M) {
+        return RISCV_EXCP_NONE;
+    }
+
     /* if bcfi not active for current env, access to csr is illegal */
     if (!cpu_get_bcfien(env)) {
 #if !defined(CONFIG_USER_ONLY)
@@ -4297,7 +4302,7 @@ static RISCVException rmw_sctrdepth(CPURISCVState *env, int csrno,
         }
 
         /* Update sctrstatus.WRPTR with a legal value */
-        depth = 16 << depth;
+        depth = 16ULL << depth;
         env->sctrstatus =
             env->sctrstatus & (~SCTRSTATUS_WRPTR_MASK | (depth - 1));
     }
diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc
index b55f56a5eb..b9c7160468 100644
--- a/target/riscv/insn_trans/trans_rvi.c.inc
+++ b/target/riscv/insn_trans/trans_rvi.c.inc
@@ -151,7 +151,9 @@ static bool trans_jalr(DisasContext *ctx, arg_jalr *a)
         tcg_gen_ext32s_tl(target_pc, target_pc);
     }
 
-    if (!has_ext(ctx, RVC) && !ctx->cfg_ptr->ext_zca) {
+    if (!riscv_cpu_allow_16bit_insn(ctx->cfg_ptr,
+                                    ctx->priv_ver,
+                                    ctx->misa_ext)) {
         TCGv t0 = tcg_temp_new();
 
         misaligned = gen_new_label();
@@ -300,7 +302,9 @@ static bool gen_branch(DisasContext *ctx, arg_b *a, TCGCond cond)
 
     gen_set_label(l); /* branch taken */
 
-    if (!has_ext(ctx, RVC) && !ctx->cfg_ptr->ext_zca &&
+    if (!riscv_cpu_allow_16bit_insn(ctx->cfg_ptr,
+                                    ctx->priv_ver,
+                                    ctx->misa_ext) &&
         (a->imm & 0x3)) {
         /* misaligned */
         TCGv target_pc = tcg_temp_new();
diff --git a/target/riscv/insn_trans/trans_rvzicfiss.c.inc b/target/riscv/insn_trans/trans_rvzicfiss.c.inc
index e3ebc4977c..b0096adcd0 100644
--- a/target/riscv/insn_trans/trans_rvzicfiss.c.inc
+++ b/target/riscv/insn_trans/trans_rvzicfiss.c.inc
@@ -15,6 +15,13 @@
  * You should have received a copy of the GNU General Public License along with
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
+
+#define REQUIRE_ZICFISS(ctx) do {        \
+    if (!ctx->cfg_ptr->ext_zicfiss) {    \
+        return false;                    \
+    }                                    \
+} while (0)
+
 static bool trans_sspopchk(DisasContext *ctx, arg_sspopchk *a)
 {
     if (!ctx->bcfi_enabled) {
@@ -77,6 +84,11 @@ static bool trans_ssrdp(DisasContext *ctx, arg_ssrdp *a)
 static bool trans_ssamoswap_w(DisasContext *ctx, arg_amoswap_w *a)
 {
     REQUIRE_A_OR_ZAAMO(ctx);
+    REQUIRE_ZICFISS(ctx);
+    if (ctx->priv == PRV_M) {
+        generate_exception(ctx, RISCV_EXCP_STORE_AMO_ACCESS_FAULT);
+    }
+
     if (!ctx->bcfi_enabled) {
         return false;
     }
@@ -97,6 +109,11 @@ static bool trans_ssamoswap_d(DisasContext *ctx, arg_amoswap_w *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_A_OR_ZAAMO(ctx);
+    REQUIRE_ZICFISS(ctx);
+    if (ctx->priv == PRV_M) {
+        generate_exception(ctx, RISCV_EXCP_STORE_AMO_ACCESS_FAULT);
+    }
+
     if (!ctx->bcfi_enabled) {
         return false;
     }
diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
index 0d4220ba93..72dc48e58d 100644
--- a/target/riscv/op_helper.c
+++ b/target/riscv/op_helper.c
@@ -279,7 +279,9 @@ target_ulong helper_sret(CPURISCVState *env)
     }
 
     target_ulong retpc = env->sepc;
-    if (!riscv_has_ext(env, RVC) && (retpc & 0x3)) {
+    if (!riscv_cpu_allow_16bit_insn(&env_archcpu(env)->cfg,
+                                    env->priv_ver,
+                                    env->misa_ext) && (retpc & 0x3)) {
         riscv_raise_exception(env, RISCV_EXCP_INST_ADDR_MIS, GETPC());
     }
 
@@ -357,7 +359,9 @@ static void check_ret_from_m_mode(CPURISCVState *env, target_ulong retpc,
         riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
     }
 
-    if (!riscv_has_ext(env, RVC) && (retpc & 0x3)) {
+    if (!riscv_cpu_allow_16bit_insn(&env_archcpu(env)->cfg,
+                                    env->priv_ver,
+                                    env->misa_ext) && (retpc & 0x3)) {
         riscv_raise_exception(env, RISCV_EXCP_INST_ADDR_MIS, GETPC());
     }
 
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index eaa5d86eae..d6651f244f 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -606,7 +606,9 @@ static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
     TCGv succ_pc = dest_gpr(ctx, rd);
 
     /* check misaligned: */
-    if (!has_ext(ctx, RVC) && !ctx->cfg_ptr->ext_zca) {
+    if (!riscv_cpu_allow_16bit_insn(ctx->cfg_ptr,
+                                    ctx->priv_ver,
+                                    ctx->misa_ext)) {
         if ((imm & 0x3) != 0) {
             TCGv target_pc = tcg_temp_new();
             gen_pc_plus_diff(target_pc, ctx, imm);
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index f7423df226..1526de96f5 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 7773df6a7c..67b3bafebb 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) {
@@ -633,47 +630,69 @@ vext_ldff(void *vd, void *v0, target_ulong base, CPURISCVState *env,
     uint32_t esz = 1 << log2_esz;
     uint32_t msize = nf * esz;
     uint32_t vma = vext_vma(desc);
-    target_ulong addr, offset, remain, page_split, elems;
+    target_ulong addr, addr_probe, addr_i, offset, remain, page_split, elems;
     int mmu_index = riscv_env_mmu_index(env, false);
+    int flags;
+    void *host;
 
-    VSTART_CHECK_EARLY_EXIT(env);
+    VSTART_CHECK_EARLY_EXIT(env, env->vl);
 
-    /* probe every access */
-    for (i = env->vstart; i < env->vl; i++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            continue;
-        }
-        addr = adjust_addr(env, base + i * (nf << log2_esz));
-        if (i == 0) {
-            /* Allow fault on first element. */
-            probe_pages(env, addr, nf << log2_esz, ra, MMU_DATA_LOAD);
-        } else {
-            remain = nf << log2_esz;
-            while (remain > 0) {
-                void *host;
-                int flags;
+    addr = base + ((env->vstart * nf) << log2_esz);
+    page_split = -(addr | TARGET_PAGE_MASK);
+    /* Get number of elements */
+    elems = page_split / msize;
+    if (unlikely(env->vstart + elems >= env->vl)) {
+        elems = env->vl - env->vstart;
+    }
 
-                offset = -(addr | TARGET_PAGE_MASK);
+    /* Check page permission/pmp/watchpoint/etc. */
+    flags = probe_access_flags(env, adjust_addr(env, addr), elems * msize,
+                               MMU_DATA_LOAD, mmu_index, true, &host, ra);
 
-                /* Probe nonfault on subsequent elements. */
-                flags = probe_access_flags(env, addr, offset, MMU_DATA_LOAD,
-                                           mmu_index, true, &host, 0);
+    /* If we are crossing a page check also the second page. */
+    if (env->vl > elems) {
+        addr_probe = addr + (elems << log2_esz);
+        flags |= probe_access_flags(env, adjust_addr(env, addr_probe),
+                                    elems * msize, MMU_DATA_LOAD, mmu_index,
+                                    true, &host, ra);
+    }
 
-                /*
-                 * Stop if invalid (unmapped) or mmio (transaction may fail).
-                 * Do not stop if watchpoint, as the spec says that
-                 * first-fault should continue to access the same
-                 * elements regardless of any watchpoint.
-                 */
-                if (flags & ~TLB_WATCHPOINT) {
-                    vl = i;
-                    goto ProbeSuccess;
+    if (flags & ~TLB_WATCHPOINT) {
+        /* probe every access */
+        for (i = env->vstart; i < env->vl; i++) {
+            if (!vm && !vext_elem_mask(v0, i)) {
+                continue;
+            }
+            addr_i = adjust_addr(env, base + i * (nf << log2_esz));
+            if (i == 0) {
+                /* Allow fault on first element. */
+                probe_pages(env, addr_i, nf << log2_esz, ra, MMU_DATA_LOAD);
+            } else {
+                remain = nf << log2_esz;
+                while (remain > 0) {
+                    offset = -(addr_i | TARGET_PAGE_MASK);
+
+                    /* Probe nonfault on subsequent elements. */
+                    flags = probe_access_flags(env, addr_i, offset,
+                                               MMU_DATA_LOAD, mmu_index, true,
+                                               &host, 0);
+
+                    /*
+                     * Stop if invalid (unmapped) or mmio (transaction may
+                     * fail). Do not stop if watchpoint, as the spec says that
+                     * first-fault should continue to access the same
+                     * elements regardless of any watchpoint.
+                     */
+                    if (flags & ~TLB_WATCHPOINT) {
+                        vl = i;
+                        goto ProbeSuccess;
+                    }
+                    if (remain <= offset) {
+                        break;
+                    }
+                    remain -= offset;
+                    addr_i = adjust_addr(env, addr_i + offset);
                 }
-                if (remain <= offset) {
-                    break;
-                }
-                remain -= offset;
-                addr = adjust_addr(env, addr + offset);
             }
         }
     }
@@ -685,15 +704,6 @@ ProbeSuccess:
 
     if (env->vstart < env->vl) {
         if (vm) {
-            /* Calculate the page range of first page */
-            addr = base + ((env->vstart * nf) << log2_esz);
-            page_split = -(addr | TARGET_PAGE_MASK);
-            /* Get number of elements */
-            elems = page_split / msize;
-            if (unlikely(env->vstart + elems >= env->vl)) {
-                elems = env->vl - env->vstart;
-            }
-
             /* Load/store elements in the first page */
             if (likely(elems)) {
                 vext_page_ldst_us(env, vd, addr, elems, nf, max_elems,
@@ -1103,7 +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));                    \
@@ -1137,7 +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));                               \
@@ -1174,7 +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));                    \
@@ -1214,7 +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));                      \
@@ -1312,7 +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)) {                              \
@@ -1361,7 +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)) {                \
@@ -1425,7 +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));                    \
@@ -1492,7 +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));                          \
@@ -2041,7 +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));                           \
@@ -2067,7 +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;                           \
@@ -2092,7 +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);            \
@@ -2118,7 +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));                           \
@@ -2165,8 +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);
-
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             /* set masked-off elements to 1s */
@@ -2190,6 +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,
@@ -2292,8 +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);
-
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             /* set masked-off elements to 1s */
@@ -2317,6 +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,
@@ -3091,7 +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)) {              \
@@ -3136,7 +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)) {              \
@@ -3724,7 +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;                                        \
@@ -4247,7 +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));                    \
@@ -4289,7 +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));                          \
@@ -4484,7 +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));                    \
@@ -4652,6 +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)) {              \
@@ -4740,6 +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)) {               \
@@ -4814,7 +4828,7 @@ 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);                       \
@@ -4904,6 +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 */
@@ -4976,6 +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 */                           \
@@ -5009,7 +5027,7 @@ 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)) {                              \
@@ -5046,7 +5064,7 @@ 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++) {                                        \
@@ -5081,7 +5099,7 @@ 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);                                      \
@@ -5125,7 +5143,7 @@ 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)) {                                \
@@ -5176,7 +5194,7 @@ 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)) {                                  \
@@ -5253,7 +5271,7 @@ 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)) {                              \
@@ -5298,7 +5316,7 @@ 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)) {                              \
@@ -5334,6 +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;                                                     \
@@ -5394,7 +5414,7 @@ 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 05b2d01e58..b490b1d398 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 a11cc8366d..8eee7e5c31 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)) {           \