Merge tag 'pull-riscv-to-apply-20220907' of https://github.com/alistair23/qemu into staging

First RISC-V PR for QEMU 7.2

* Update [m|h]tinst CSR in interrupt handling
* Force disable extensions if priv spec version does not match
* fix shifts shamt value for rv128c
* move zmmul out of the experimental
* virt: pass random seed to fdt
* Add checks for supported extension combinations
* Upgrade OpenSBI to v1.1
* Fix typo and restore Pointer Masking functionality for RISC-V
* Add mask agnostic behaviour (rvv_ma_all_1s) for vector extension
* Add Zihintpause support
* opentitan: bump opentitan version
* microchip_pfsoc: fix kernel panics due to missing peripherals
* Remove additional priv version check for mcountinhibit
* virt machine device tree improvements
* Add xicondops in ISA entry
* Use official extension names for AIA CSRs

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEE9sSsRtSTSGjTuM6PIeENKd+XcFQFAmMYUCUACgkQIeENKd+X
# cFRpEQf/T1FFcGq3TZrEPmqMdFPUSb+SEJNgwYFfloqkNjB2HIFbd2tKWAE1Tgjr
# esV00p7YPyox1Ct+fKdwSxDxRSN9OI56v+nI8ZFwluVu7vpChuTFmOHur8rNxl1T
# 8MZgP2kMxMOJSnyHCS2iV9AUFdTExS65DbmlAKzi5fpBtt9jYTPSXsI49MP8+Ku/
# 1gdv5ZF5BXDJsGs7xHvE92dRzQEVN+As64IjlknFHHpmCM1b+Ah3GekXUbKmBuDG
# /NaZyZNPCYxdRmPm/D7k0SOMZSJ9sLyhXTetZ0ZpBxG1ioClX37yS5wn4NLsCz/2
# fXrnML+MQFUKZ03AZ9lWvxcu7kXfWA==
# =7mGD
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 07 Sep 2022 04:02:45 EDT
# gpg:                using RSA key F6C4AC46D4934868D3B8CE8F21E10D29DF977054
# gpg: Good signature from "Alistair Francis <alistair@alistair23.me>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: F6C4 AC46 D493 4868 D3B8  CE8F 21E1 0D29 DF97 7054

* tag 'pull-riscv-to-apply-20220907' of https://github.com/alistair23/qemu: (44 commits)
  target/riscv: Update the privilege field for sscofpmf CSRs
  hw/riscv: virt: Add PMU DT node to the device tree
  target/riscv: Add few cache related PMU events
  target/riscv: Simplify counter predicate function
  target/riscv: Add sscofpmf extension support
  target/riscv: Add vstimecmp support
  target/riscv: Add stimecmp support
  hw/intc: Move mtimer/mtimecmp to aclint
  target/riscv: Use official extension names for AIA CSRs
  target/riscv: Add xicondops in ISA entry
  hw/core: fix platform bus node name
  hw/riscv: virt: fix syscon subnode paths
  hw/riscv: virt: fix the plic's address cells
  hw/riscv: virt: fix uart node name
  target/riscv: Remove additional priv version check for mcountinhibit
  hw/riscv: microchip_pfsoc: fix kernel panics due to missing peripherals
  hw/riscv: opentitan: bump opentitan version
  target/riscv: Fix priority of csr related check in riscv_csrrw_check
  hw/riscv: remove 'fdt' param from riscv_setup_rom_reset_vec()
  target/riscv: Add Zihintpause support
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 129 insertions, 23 deletions

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index a96fc49c71..d224861c2c 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -127,6 +127,11 @@ static inline uint32_t vext_vta(uint32_t desc)
     return FIELD_EX32(simd_data(desc), VDATA, VTA);
 }
 
+static inline uint32_t vext_vma(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, VMA);
+}
+
 static inline uint32_t vext_vta_all_1s(uint32_t desc)
 {
     return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
@@ -278,14 +283,18 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
     uint32_t esz = 1 << log2_esz;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
 
     for (i = env->vstart; i < env->vl; i++, env->vstart++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            continue;
-        }
-
         k = 0;
         while (k < nf) {
+            if (!vm && !vext_elem_mask(v0, i)) {
+                /* set masked-off elements to 1s */
+                vext_set_elems_1s(vd, vma, (i + k * max_elems) * esz,
+                                  (i + k * max_elems + 1) * esz);
+                k++;
+                continue;
+            }
             target_ulong addr = base + stride * i + (k << log2_esz);
             ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
             k++;
@@ -477,15 +486,19 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
     uint32_t esz = 1 << log2_esz;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
 
     /* load bytes from guest memory */
     for (i = env->vstart; i < env->vl; i++, env->vstart++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            continue;
-        }
-
         k = 0;
         while (k < nf) {
+            if (!vm && !vext_elem_mask(v0, i)) {
+                /* set masked-off elements to 1s */
+                vext_set_elems_1s(vd, vma, (i + k * max_elems) * esz,
+                                  (i + k * max_elems + 1) * esz);
+                k++;
+                continue;
+            }
             abi_ptr addr = get_index_addr(base, i, vs2) + (k << log2_esz);
             ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
             k++;
@@ -574,6 +587,7 @@ vext_ldff(void *vd, void *v0, target_ulong base,
     uint32_t esz = 1 << log2_esz;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
     target_ulong addr, offset, remain;
 
     /* probe every access*/
@@ -619,10 +633,14 @@ ProbeSuccess:
     }
     for (i = env->vstart; i < env->vl; i++) {
         k = 0;
-        if (!vm && !vext_elem_mask(v0, i)) {
-            continue;
-        }
         while (k < nf) {
+            if (!vm && !vext_elem_mask(v0, i)) {
+                /* set masked-off elements to 1s */
+                vext_set_elems_1s(vd, vma, (i + k * max_elems) * esz,
+                                  (i + k * max_elems + 1) * esz);
+                k++;
+                continue;
+            }
             target_ulong addr = base + ((i * nf + k) << log2_esz);
             ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
             k++;
@@ -812,10 +830,13 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
     uint32_t vl = env->vl;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
     uint32_t i;
 
     for (i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
             continue;
         }
         fn(vd, vs1, vs2, i);
@@ -878,10 +899,13 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
     uint32_t vl = env->vl;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
     uint32_t i;
 
     for (i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
             continue;
         }
         fn(vd, s1, vs2, i);
@@ -1274,10 +1298,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,                          \
     uint32_t esz = sizeof(TS1);                                           \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     uint32_t i;                                                           \
                                                                           \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         TS1 s1 = *((TS1 *)vs1 + HS1(i));                                  \
@@ -1315,10 +1342,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,      \
     uint32_t total_elems =                                  \
         vext_get_total_elems(env, desc, esz);               \
     uint32_t vta = vext_vta(desc);                          \
+    uint32_t vma = vext_vma(desc);                          \
     uint32_t i;                                             \
                                                             \
     for (i = env->vstart; i < vl; i++) {                    \
         if (!vm && !vext_elem_mask(v0, i)) {                \
+            /* set masked-off elements to 1s */             \
+            vext_set_elems_1s(vd, vma, i * esz,             \
+                              (i + 1) * esz);               \
             continue;                                       \
         }                                                   \
         TS2 s2 = *((TS2 *)vs2 + HS2(i));                    \
@@ -1373,12 +1404,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
     uint32_t vl = env->vl;                                    \
     uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
+    uint32_t vma = vext_vma(desc);                            \
     uint32_t i;                                               \
                                                               \
     for (i = env->vstart; i < vl; i++) {                      \
         ETYPE s1 = *((ETYPE *)vs1 + H(i));                    \
         ETYPE s2 = *((ETYPE *)vs2 + H(i));                    \
         if (!vm && !vext_elem_mask(v0, i)) {                  \
+            /* set masked-off elements to 1s */               \
+            if (vma) {                                        \
+                vext_set_elem_mask(vd, i, 1);                 \
+            }                                                 \
             continue;                                         \
         }                                                     \
         vext_set_elem_mask(vd, i, DO_OP(s2, s1));             \
@@ -1431,11 +1467,16 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,   \
     uint32_t vl = env->vl;                                          \
     uint32_t total_elems = env_archcpu(env)->cfg.vlen;              \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);                    \
+    uint32_t vma = vext_vma(desc);                                  \
     uint32_t i;                                                     \
                                                                     \
     for (i = env->vstart; i < vl; i++) {                            \
         ETYPE s2 = *((ETYPE *)vs2 + H(i));                          \
         if (!vm && !vext_elem_mask(v0, i)) {                        \
+            /* set masked-off elements to 1s */                     \
+            if (vma) {                                              \
+                vext_set_elem_mask(vd, i, 1);                       \
+            }                                                       \
             continue;                                               \
         }                                                           \
         vext_set_elem_mask(vd, i,                                   \
@@ -2088,10 +2129,12 @@ static inline void
 vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
              CPURISCVState *env,
              uint32_t vl, uint32_t vm, int vxrm,
-             opivv2_rm_fn *fn)
+             opivv2_rm_fn *fn, uint32_t vma, uint32_t esz)
 {
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
             continue;
         }
         fn(vd, vs1, vs2, i, env, vxrm);
@@ -2109,23 +2152,24 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
     uint32_t vl = env->vl;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
 
     switch (env->vxrm) {
     case 0: /* rnu */
         vext_vv_rm_1(vd, v0, vs1, vs2,
-                     env, vl, vm, 0, fn);
+                     env, vl, vm, 0, fn, vma, esz);
         break;
     case 1: /* rne */
         vext_vv_rm_1(vd, v0, vs1, vs2,
-                     env, vl, vm, 1, fn);
+                     env, vl, vm, 1, fn, vma, esz);
         break;
     case 2: /* rdn */
         vext_vv_rm_1(vd, v0, vs1, vs2,
-                     env, vl, vm, 2, fn);
+                     env, vl, vm, 2, fn, vma, esz);
         break;
     default: /* rod */
         vext_vv_rm_1(vd, v0, vs1, vs2,
-                     env, vl, vm, 3, fn);
+                     env, vl, vm, 3, fn, vma, esz);
         break;
     }
     /* set tail elements to 1s */
@@ -2209,10 +2253,12 @@ static inline void
 vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
              CPURISCVState *env,
              uint32_t vl, uint32_t vm, int vxrm,
-             opivx2_rm_fn *fn)
+             opivx2_rm_fn *fn, uint32_t vma, uint32_t esz)
 {
     for (uint32_t i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
             continue;
         }
         fn(vd, s1, vs2, i, env, vxrm);
@@ -2230,23 +2276,24 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
     uint32_t vl = env->vl;
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);
     uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
 
     switch (env->vxrm) {
     case 0: /* rnu */
         vext_vx_rm_1(vd, v0, s1, vs2,
-                     env, vl, vm, 0, fn);
+                     env, vl, vm, 0, fn, vma, esz);
         break;
     case 1: /* rne */
         vext_vx_rm_1(vd, v0, s1, vs2,
-                     env, vl, vm, 1, fn);
+                     env, vl, vm, 1, fn, vma, esz);
         break;
     case 2: /* rdn */
         vext_vx_rm_1(vd, v0, s1, vs2,
-                     env, vl, vm, 2, fn);
+                     env, vl, vm, 2, fn, vma, esz);
         break;
     default: /* rod */
         vext_vx_rm_1(vd, v0, s1, vs2,
-                     env, vl, vm, 3, fn);
+                     env, vl, vm, 3, fn, vma, esz);
         break;
     }
     /* set tail elements to 1s */
@@ -3004,10 +3051,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
     uint32_t total_elems =                                \
         vext_get_total_elems(env, desc, ESZ);             \
     uint32_t vta = vext_vta(desc);                        \
+    uint32_t vma = vext_vma(desc);                        \
     uint32_t i;                                           \
                                                           \
     for (i = env->vstart; i < vl; i++) {                  \
         if (!vm && !vext_elem_mask(v0, i)) {              \
+            /* set masked-off elements to 1s */           \
+            vext_set_elems_1s(vd, vma, i * ESZ,           \
+                              (i + 1) * ESZ);             \
             continue;                                     \
         }                                                 \
         do_##NAME(vd, vs1, vs2, i, env);                  \
@@ -3043,10 +3094,14 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1,        \
     uint32_t total_elems =                                \
         vext_get_total_elems(env, desc, ESZ);              \
     uint32_t vta = vext_vta(desc);                        \
+    uint32_t vma = vext_vma(desc);                        \
     uint32_t i;                                           \
                                                           \
     for (i = env->vstart; i < vl; i++) {                  \
         if (!vm && !vext_elem_mask(v0, i)) {              \
+            /* set masked-off elements to 1s */           \
+            vext_set_elems_1s(vd, vma, i * ESZ,           \
+                              (i + 1) * ESZ);             \
             continue;                                     \
         }                                                 \
         do_##NAME(vd, s1, vs2, i, env);                   \
@@ -3618,6 +3673,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
     uint32_t total_elems =                             \
         vext_get_total_elems(env, desc, ESZ);          \
     uint32_t vta = vext_vta(desc);                     \
+    uint32_t vma = vext_vma(desc);                     \
     uint32_t i;                                        \
                                                        \
     if (vl == 0) {                                     \
@@ -3625,6 +3681,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
     }                                                  \
     for (i = env->vstart; i < vl; i++) {               \
         if (!vm && !vext_elem_mask(v0, i)) {           \
+            /* set masked-off elements to 1s */        \
+            vext_set_elems_1s(vd, vma, i * ESZ,        \
+                              (i + 1) * ESZ);          \
             continue;                                  \
         }                                              \
         do_##NAME(vd, vs2, i, env);                    \
@@ -4135,12 +4194,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
     uint32_t vl = env->vl;                                    \
     uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
+    uint32_t vma = vext_vma(desc);                            \
     uint32_t i;                                               \
                                                               \
     for (i = env->vstart; i < vl; i++) {                      \
         ETYPE s1 = *((ETYPE *)vs1 + H(i));                    \
         ETYPE s2 = *((ETYPE *)vs2 + H(i));                    \
         if (!vm && !vext_elem_mask(v0, i)) {                  \
+            /* set masked-off elements to 1s */               \
+            if (vma) {                                        \
+                vext_set_elem_mask(vd, i, 1);                 \
+            }                                                 \
             continue;                                         \
         }                                                     \
         vext_set_elem_mask(vd, i,                             \
@@ -4168,11 +4232,16 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2,       \
     uint32_t vl = env->vl;                                          \
     uint32_t total_elems = env_archcpu(env)->cfg.vlen;              \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);                    \
+    uint32_t vma = vext_vma(desc);                                  \
     uint32_t i;                                                     \
                                                                     \
     for (i = env->vstart; i < vl; i++) {                            \
         ETYPE s2 = *((ETYPE *)vs2 + H(i));                          \
         if (!vm && !vext_elem_mask(v0, i)) {                        \
+            /* set masked-off elements to 1s */                     \
+            if (vma) {                                              \
+                vext_set_elem_mask(vd, i, 1);                       \
+            }                                                       \
             continue;                                               \
         }                                                           \
         vext_set_elem_mask(vd, i,                                   \
@@ -4295,10 +4364,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
     uint32_t total_elems =                             \
         vext_get_total_elems(env, desc, ESZ);          \
     uint32_t vta = vext_vta(desc);                     \
+    uint32_t vma = vext_vma(desc);                     \
     uint32_t i;                                        \
                                                        \
     for (i = env->vstart; i < vl; i++) {               \
         if (!vm && !vext_elem_mask(v0, i)) {           \
+            /* set masked-off elements to 1s */        \
+            vext_set_elems_1s(vd, vma, i * ESZ,        \
+                              (i + 1) * ESZ);          \
             continue;                                  \
         }                                              \
         do_##NAME(vd, vs2, i);                         \
@@ -4806,11 +4879,16 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
     uint32_t vl = env->vl;
     uint32_t total_elems = env_archcpu(env)->cfg.vlen;
     uint32_t vta_all_1s = vext_vta_all_1s(desc);
+    uint32_t vma = vext_vma(desc);
     int i;
     bool first_mask_bit = false;
 
     for (i = env->vstart; i < vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            if (vma) {
+                vext_set_elem_mask(vd, i, 1);
+            }
             continue;
         }
         /* write a zero to all following active elements */
@@ -4871,11 +4949,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env,      \
     uint32_t esz = sizeof(ETYPE);                                         \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     uint32_t sum = 0;                                                     \
     int i;                                                                \
                                                                           \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         *((ETYPE *)vd + H(i)) = sum;                                      \
@@ -4902,10 +4983,13 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc)  \
     uint32_t esz = sizeof(ETYPE);                                         \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     int i;                                                                \
                                                                           \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         *((ETYPE *)vd + H(i)) = i;                                        \
@@ -4934,11 +5018,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,         \
     uint32_t esz = sizeof(ETYPE);                                         \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     target_ulong offset = s1, i_min, i;                                   \
                                                                           \
     i_min = MAX(env->vstart, offset);                                     \
     for (i = i_min; i < vl; i++) {                                        \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset));          \
@@ -4963,13 +5050,17 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,         \
     uint32_t esz = sizeof(ETYPE);                                         \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     target_ulong i_max, i;                                                \
                                                                           \
     i_max = MAX(MIN(s1 < vlmax ? vlmax - s1 : 0, vl), env->vstart);       \
     for (i = env->vstart; i < i_max; ++i) {                               \
-        if (vm || vext_elem_mask(v0, i)) {                                \
-            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + s1));          \
+        if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
+            continue;                                                     \
         }                                                                 \
+        *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + s1));              \
     }                                                                     \
                                                                           \
     for (i = i_max; i < vl; ++i) {                                        \
@@ -4999,10 +5090,13 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1,       \
     uint32_t esz = sizeof(ETYPE);                                           \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);            \
     uint32_t vta = vext_vta(desc);                                          \
+    uint32_t vma = vext_vma(desc);                                          \
     uint32_t i;                                                             \
                                                                             \
     for (i = env->vstart; i < vl; i++) {                                    \
         if (!vm && !vext_elem_mask(v0, i)) {                                \
+            /* set masked-off elements to 1s */                             \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);             \
             continue;                                                       \
         }                                                                   \
         if (i == 0) {                                                       \
@@ -5044,10 +5138,13 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1,       \
     uint32_t esz = sizeof(ETYPE);                                             \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);              \
     uint32_t vta = vext_vta(desc);                                            \
+    uint32_t vma = vext_vma(desc);                                            \
     uint32_t i;                                                               \
                                                                               \
     for (i = env->vstart; i < vl; i++) {                                      \
         if (!vm && !vext_elem_mask(v0, i)) {                                  \
+            /* set masked-off elements to 1s */                               \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);               \
             continue;                                                         \
         }                                                                     \
         if (i == vl - 1) {                                                    \
@@ -5115,11 +5212,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,               \
     uint32_t esz = sizeof(TS2);                                           \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     uint64_t index;                                                       \
     uint32_t i;                                                           \
                                                                           \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         index = *((TS1 *)vs1 + HS1(i));                                   \
@@ -5155,11 +5255,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,         \
     uint32_t esz = sizeof(ETYPE);                                         \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz);          \
     uint32_t vta = vext_vta(desc);                                        \
+    uint32_t vma = vext_vma(desc);                                        \
     uint64_t index = s1;                                                  \
     uint32_t i;                                                           \
                                                                           \
     for (i = env->vstart; i < vl; i++) {                                  \
         if (!vm && !vext_elem_mask(v0, i)) {                              \
+            /* set masked-off elements to 1s */                           \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);           \
             continue;                                                     \
         }                                                                 \
         if (index >= vlmax) {                                             \
@@ -5234,10 +5337,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,                 \
     uint32_t esz = sizeof(ETYPE);                                \
     uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
     uint32_t vta = vext_vta(desc);                               \
+    uint32_t vma = vext_vma(desc);                               \
     uint32_t i;                                                  \
                                                                  \
     for (i = env->vstart; i < vl; i++) {                         \
         if (!vm && !vext_elem_mask(v0, i)) {                     \
+            /* set masked-off elements to 1s */                  \
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);  \
             continue;                                            \
         }                                                        \
         *((ETYPE *)vd + HD(i)) = *((DTYPE *)vs2 + HS1(i));       \