Merge tag 's390x-tcg-2019-06-07' into s390-next-staging

Finalize implementation of the "Vector Facility" for s390x TCG. Add it
to the QEMU CPU model, so it is enabled as default.
Also:
- One fix (and one workaround) for the STFLE instruction
- Fix the alignment of vector registers (and change the data type)
- Properly generate ELF_HWCAP for s390x for linux-user
- Use a gvec helper for VECTOR SELECT

# gpg: Signature made Fri 07 Jun 2019 02:58:01 PM CEST
# gpg:                using RSA key 1BD9CAAD735C4C3A460DFCCA4DDE10F700FF835A
# gpg:                issuer "david@redhat.com"
# gpg: Good signature from "David Hildenbrand <david@redhat.com>" [full]
# gpg:                 aka "David Hildenbrand <davidhildenbrand@gmail.com>" [full]

* tag 's390x-tcg-2019-06-07': (33 commits)
  linux-user: elf: ELF_HWCAP for s390x
  s390x/tcg: Use tcg_gen_gvec_bitsel for VECTOR SELECT
  s390x: Bump the "qemu" CPU model up to a stripped-down z13
  s390x/tcg: We support the Vector Facility
  s390x/tcg: Allow linux-user to use vector instructions
  s390x/tcg: Implement VECTOR FP TEST DATA CLASS IMMEDIATE
  s390x/tcg: Implement VECTOR FP SUBTRACT
  s390x/tcg: Implement VECTOR FP SQUARE ROOT
  s390x/tcg: Implement VECTOR FP PERFORM SIGN OPERATION
  s390x/tcg: Implement VECTOR FP MULTIPLY AND (ADD|SUBTRACT)
  s390x/tcg: Implement VECTOR FP MULTIPLY
  s390x/tcg: Implement VECTOR LOAD ROUNDED
  s390x/tcg: Implement VECTOR LOAD LENGTHENED
  s390x/tcg: Implement VECTOR LOAD FP INTEGER
  s390x/tcg: Implement VECTOR FP DIVIDE
  s390x/tcg: Implement VECTOR FP CONVERT TO LOGICAL 64-BIT
  s390x/tcg: Implement VECTOR FP CONVERT TO FIXED 64-BIT
  s390x/tcg: Implement VECTOR FP CONVERT FROM LOGICAL 64-BIT
  s390x/tcg: Implement VECTOR FP CONVERT FROM FIXED 64-BIT
  s390x/tcg: Implement VECTOR FP COMPARE (EQUAL|HIGH|HIGH OR EQUAL)
  ...

Signed-off-by: Cornelia Huck <cohuck@redhat.com>

26 files changed, 1930 insertions, 139 deletions

diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index bbc6e8fa0b..4d643686cb 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -669,7 +669,9 @@ DEFINE_CCW_MACHINE(4_1, "4.1", true);
 
 static void ccw_machine_4_0_instance_options(MachineState *machine)
 {
+    static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V4_0 };
     ccw_machine_4_1_instance_options(machine);
+    s390_set_qemu_cpu_model(0x2827, 12, 2, qemu_cpu_feat);
 }
 
 static void ccw_machine_4_0_class_options(MachineClass *mc)
diff --git a/include/elf.h b/include/elf.h
index ea7708a4ea..3501e0c8d0 100644
--- a/include/elf.h
+++ b/include/elf.h
@@ -598,6 +598,7 @@ typedef struct {
 #define HWCAP_S390_ETF3EH       256
 #define HWCAP_S390_HIGH_GPRS    512
 #define HWCAP_S390_TE           1024
+#define HWCAP_S390_VXRS         2048
 
 /* M68K specific definitions. */
 /* We use the top 24 bits to encode information about the
diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index a57b7049dd..5451d262ec 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -1308,6 +1308,34 @@ static inline void init_thread(struct target_pt_regs *regs,
 #define ELF_DATA	ELFDATA2MSB
 #define ELF_ARCH	EM_S390
 
+#include "elf.h"
+
+#define ELF_HWCAP get_elf_hwcap()
+
+#define GET_FEATURE(_feat, _hwcap) \
+    do { if (s390_has_feat(_feat)) { hwcap |= _hwcap; } } while (0)
+
+static uint32_t get_elf_hwcap(void)
+{
+    /*
+     * Let's assume we always have esan3 and zarch.
+     * 31-bit processes can use 64-bit registers (high gprs).
+     */
+    uint32_t hwcap = HWCAP_S390_ESAN3 | HWCAP_S390_ZARCH | HWCAP_S390_HIGH_GPRS;
+
+    GET_FEATURE(S390_FEAT_STFLE, HWCAP_S390_STFLE);
+    GET_FEATURE(S390_FEAT_MSA, HWCAP_S390_MSA);
+    GET_FEATURE(S390_FEAT_LONG_DISPLACEMENT, HWCAP_S390_LDISP);
+    GET_FEATURE(S390_FEAT_EXTENDED_IMMEDIATE, HWCAP_S390_EIMM);
+    if (s390_has_feat(S390_FEAT_EXTENDED_TRANSLATION_3) &&
+        s390_has_feat(S390_FEAT_ETF3_ENH)) {
+        hwcap |= HWCAP_S390_ETF3EH;
+    }
+    GET_FEATURE(S390_FEAT_VECTOR, HWCAP_S390_VXRS);
+
+    return hwcap;
+}
+
 static inline void init_thread(struct target_pt_regs *regs, struct image_info *infop)
 {
     regs->psw.addr = infop->entry;
diff --git a/linux-user/s390x/signal.c b/linux-user/s390x/signal.c
index 3d3cb67bbe..ecfa2a14a9 100644
--- a/linux-user/s390x/signal.c
+++ b/linux-user/s390x/signal.c
@@ -123,7 +123,7 @@ static void save_sigregs(CPUS390XState *env, target_sigregs *sregs)
      */
     //save_fp_regs(&current->thread.fp_regs); FIXME
     for (i = 0; i < 16; i++) {
-        __put_user(get_freg(env, i)->ll, &sregs->fpregs.fprs[i]);
+        __put_user(*get_freg(env, i), &sregs->fpregs.fprs[i]);
     }
 }
 
@@ -254,7 +254,7 @@ restore_sigregs(CPUS390XState *env, target_sigregs *sc)
         __get_user(env->aregs[i], &sc->regs.acrs[i]);
     }
     for (i = 0; i < 16; i++) {
-        __get_user(get_freg(env, i)->ll, &sc->fpregs.fprs[i]);
+        __get_user(*get_freg(env, i), &sc->fpregs.fprs[i]);
     }
 
     return err;
diff --git a/target/s390x/Makefile.objs b/target/s390x/Makefile.objs
index 0316457880..3e2745594a 100644
--- a/target/s390x/Makefile.objs
+++ b/target/s390x/Makefile.objs
@@ -1,7 +1,8 @@
 obj-y += cpu.o cpu_models.o cpu_features.o gdbstub.o interrupt.o helper.o
 obj-$(CONFIG_TCG) += translate.o cc_helper.o excp_helper.o fpu_helper.o
 obj-$(CONFIG_TCG) += int_helper.o mem_helper.o misc_helper.o crypto_helper.o
-obj-$(CONFIG_TCG) += vec_helper.o vec_int_helper.o
+obj-$(CONFIG_TCG) += vec_helper.o vec_int_helper.o vec_string_helper.o
+obj-$(CONFIG_TCG) += vec_fpu_helper.o
 obj-$(CONFIG_SOFTMMU) += machine.o ioinst.o arch_dump.o mmu_helper.o diag.o
 obj-$(CONFIG_SOFTMMU) += sigp.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c
index c9ef0a6e60..50fa0ae4b6 100644
--- a/target/s390x/arch_dump.c
+++ b/target/s390x/arch_dump.c
@@ -104,7 +104,7 @@ static void s390x_write_elf64_fpregset(Note *note, S390CPU *cpu, int id)
     note->hdr.n_type = cpu_to_be32(NT_FPREGSET);
     note->contents.fpregset.fpc = cpu_to_be32(cpu->env.fpc);
     for (i = 0; i <= 15; i++) {
-        note->contents.fpregset.fprs[i] = cpu_to_be64(get_freg(cs, i)->ll);
+        note->contents.fpregset.fprs[i] = cpu_to_be64(*get_freg(cs, i));
     }
 }
 
@@ -114,7 +114,7 @@ static void s390x_write_elf64_vregslo(Note *note, S390CPU *cpu,  int id)
 
     note->hdr.n_type = cpu_to_be32(NT_S390_VXRS_LOW);
     for (i = 0; i <= 15; i++) {
-        note->contents.vregslo.vregs[i] = cpu_to_be64(cpu->env.vregs[i][1].ll);
+        note->contents.vregslo.vregs[i] = cpu_to_be64(cpu->env.vregs[i][1]);
     }
 }
 
@@ -127,8 +127,8 @@ static void s390x_write_elf64_vregshi(Note *note, S390CPU *cpu, int id)
 
     note->hdr.n_type = cpu_to_be32(NT_S390_VXRS_HIGH);
     for (i = 0; i <= 15; i++) {
-        temp_vregshi->vregs[i][0] = cpu_to_be64(cpu->env.vregs[i + 16][0].ll);
-        temp_vregshi->vregs[i][1] = cpu_to_be64(cpu->env.vregs[i + 16][1].ll);
+        temp_vregshi->vregs[i][0] = cpu_to_be64(cpu->env.vregs[i + 16][0]);
+        temp_vregshi->vregs[i][1] = cpu_to_be64(cpu->env.vregs[i + 16][1]);
     }
 }
 
diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c
index b1df63d82c..6af1a1530f 100644
--- a/target/s390x/cpu.c
+++ b/target/s390x/cpu.c
@@ -145,6 +145,9 @@ static void s390_cpu_full_reset(CPUState *s)
 #if defined(CONFIG_USER_ONLY)
     /* user mode should always be allowed to use the full FPU */
     env->cregs[0] |= CR0_AFP;
+    if (s390_has_feat(S390_FEAT_VECTOR)) {
+        env->cregs[0] |= CR0_VECTOR;
+    }
 #endif
 
     /* architectured initial value for Breaking-Event-Address register */
diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h
index 7305cacc7b..4fc08a2c88 100644
--- a/target/s390x/cpu.h
+++ b/target/s390x/cpu.h
@@ -66,7 +66,7 @@ struct CPUS390XState {
      * The floating point registers are part of the vector registers.
      * vregs[0][0] -> vregs[15][0] are 16 floating point registers
      */
-    CPU_DoubleU vregs[32][2];  /* vector registers */
+    uint64_t vregs[32][2] QEMU_ALIGNED(16);  /* vector registers */
     uint32_t aregs[16];    /* access registers */
     uint8_t riccb[64];     /* runtime instrumentation control */
     uint64_t gscb[4];      /* guarded storage control */
@@ -153,7 +153,7 @@ struct CPUS390XState {
 
 };
 
-static inline CPU_DoubleU *get_freg(CPUS390XState *cs, int nr)
+static inline uint64_t *get_freg(CPUS390XState *cs, int nr)
 {
     return &cs->vregs[nr][0];
 }
@@ -215,6 +215,7 @@ extern const struct VMStateDescription vmstate_s390_cpu;
 #define PGM_SPECIAL_OP                  0x0013
 #define PGM_OPERAND                     0x0015
 #define PGM_TRACE_TABLE                 0x0016
+#define PGM_VECTOR_PROCESSING           0x001b
 #define PGM_SPACE_SWITCH                0x001c
 #define PGM_HFP_SQRT                    0x001d
 #define PGM_PC_TRANS_SPEC               0x001f
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 21ea819483..b5d16e4c89 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -86,8 +86,8 @@ static S390CPUDef s390_cpu_defs[] = {
     CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM 8562 GA1"),
 };
 
-#define QEMU_MAX_CPU_TYPE 0x2827
-#define QEMU_MAX_CPU_GEN 12
+#define QEMU_MAX_CPU_TYPE 0x2964
+#define QEMU_MAX_CPU_GEN 13
 #define QEMU_MAX_CPU_EC_GA 2
 static const S390FeatInit qemu_max_cpu_feat_init = { S390_FEAT_LIST_QEMU_MAX };
 static S390FeatBitmap qemu_max_cpu_feat;
diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c
index 3a467b72c5..f21bcf79ae 100644
--- a/target/s390x/excp_helper.c
+++ b/target/s390x/excp_helper.c
@@ -62,6 +62,21 @@ void QEMU_NORETURN tcg_s390_data_exception(CPUS390XState *env, uint32_t dxc,
     tcg_s390_program_interrupt(env, PGM_DATA, ILEN_AUTO, ra);
 }
 
+void QEMU_NORETURN tcg_s390_vector_exception(CPUS390XState *env, uint32_t vxc,
+                                             uintptr_t ra)
+{
+    g_assert(vxc <= 0xff);
+#if !defined(CONFIG_USER_ONLY)
+    /* Always store the VXC into the lowcore, without AFP it is undefined */
+    stl_phys(CPU(s390_env_get_cpu(env))->as,
+             env->psa + offsetof(LowCore, data_exc_code), vxc);
+#endif
+
+    /* Always store the VXC into the FPC, without AFP it is undefined */
+    env->fpc = deposit32(env->fpc, 8, 8, vxc);
+    tcg_s390_program_interrupt(env, PGM_VECTOR_PROCESSING, ILEN_AUTO, ra);
+}
+
 void HELPER(data_exception)(CPUS390XState *env, uint32_t dxc)
 {
     tcg_s390_data_exception(env, dxc, GETPC());
@@ -390,8 +405,8 @@ static int mchk_store_vregs(CPUS390XState *env, uint64_t mcesao)
     }
 
     for (i = 0; i < 32; i++) {
-        sa->vregs[i][0] = cpu_to_be64(env->vregs[i][0].ll);
-        sa->vregs[i][1] = cpu_to_be64(env->vregs[i][1].ll);
+        sa->vregs[i][0] = cpu_to_be64(env->vregs[i][0]);
+        sa->vregs[i][1] = cpu_to_be64(env->vregs[i][1]);
     }
 
     cpu_physical_memory_unmap(sa, len, 1, len);
@@ -429,7 +444,7 @@ static void do_mchk_interrupt(CPUS390XState *env)
     lowcore->ar_access_id = 1;
 
     for (i = 0; i < 16; i++) {
-        lowcore->floating_pt_save_area[i] = cpu_to_be64(get_freg(env, i)->ll);
+        lowcore->floating_pt_save_area[i] = cpu_to_be64(*get_freg(env, i));
         lowcore->gpregs_save_area[i] = cpu_to_be64(env->regs[i]);
         lowcore->access_regs_save_area[i] = cpu_to_be32(env->aregs[i]);
         lowcore->cregs_save_area[i] = cpu_to_be64(env->cregs[i]);
diff --git a/target/s390x/fpu_helper.c b/target/s390x/fpu_helper.c
index 1be68bafea..d2c17ed942 100644
--- a/target/s390x/fpu_helper.c
+++ b/target/s390x/fpu_helper.c
@@ -112,7 +112,7 @@ static void handle_exceptions(CPUS390XState *env, bool XxC, uintptr_t retaddr)
     }
 }
 
-static inline int float_comp_to_cc(CPUS390XState *env, int float_compare)
+int float_comp_to_cc(CPUS390XState *env, int float_compare)
 {
     S390CPU *cpu = s390_env_get_cpu(env);
 
@@ -746,7 +746,7 @@ static inline uint16_t dcmask(int bit, bool neg)
 }
 
 #define DEF_FLOAT_DCMASK(_TYPE) \
-static uint16_t _TYPE##_dcmask(CPUS390XState *env, _TYPE f1)       \
+uint16_t _TYPE##_dcmask(CPUS390XState *env, _TYPE f1)              \
 {                                                                  \
     const bool neg = _TYPE##_is_neg(f1);                           \
                                                                    \
diff --git a/target/s390x/gdbstub.c b/target/s390x/gdbstub.c
index df147596ce..9cfd8fe3e0 100644
--- a/target/s390x/gdbstub.c
+++ b/target/s390x/gdbstub.c
@@ -116,7 +116,7 @@ static int cpu_read_fp_reg(CPUS390XState *env, uint8_t *mem_buf, int n)
     case S390_FPC_REGNUM:
         return gdb_get_reg32(mem_buf, env->fpc);
     case S390_F0_REGNUM ... S390_F15_REGNUM:
-        return gdb_get_reg64(mem_buf, get_freg(env, n - S390_F0_REGNUM)->ll);
+        return gdb_get_reg64(mem_buf, *get_freg(env, n - S390_F0_REGNUM));
     default:
         return 0;
     }
@@ -129,7 +129,7 @@ static int cpu_write_fp_reg(CPUS390XState *env, uint8_t *mem_buf, int n)
         env->fpc = ldl_p(mem_buf);
         return 4;
     case S390_F0_REGNUM ... S390_F15_REGNUM:
-        get_freg(env, n - S390_F0_REGNUM)->ll = ldtul_p(mem_buf);
+        *get_freg(env, n - S390_F0_REGNUM) = ldtul_p(mem_buf);
         return 8;
     default:
         return 0;
@@ -150,11 +150,11 @@ static int cpu_read_vreg(CPUS390XState *env, uint8_t *mem_buf, int n)
 
     switch (n) {
     case S390_V0L_REGNUM ... S390_V15L_REGNUM:
-        ret = gdb_get_reg64(mem_buf, env->vregs[n][1].ll);
+        ret = gdb_get_reg64(mem_buf, env->vregs[n][1]);
         break;
     case S390_V16_REGNUM ... S390_V31_REGNUM:
-        ret = gdb_get_reg64(mem_buf, env->vregs[n][0].ll);
-        ret += gdb_get_reg64(mem_buf + 8, env->vregs[n][1].ll);
+        ret = gdb_get_reg64(mem_buf, env->vregs[n][0]);
+        ret += gdb_get_reg64(mem_buf + 8, env->vregs[n][1]);
         break;
     default:
         ret = 0;
@@ -167,11 +167,11 @@ static int cpu_write_vreg(CPUS390XState *env, uint8_t *mem_buf, int n)
 {
     switch (n) {
     case S390_V0L_REGNUM ... S390_V15L_REGNUM:
-        env->vregs[n][1].ll = ldtul_p(mem_buf + 8);
+        env->vregs[n][1] = ldtul_p(mem_buf + 8);
         return 8;
     case S390_V16_REGNUM ... S390_V31_REGNUM:
-        env->vregs[n][0].ll = ldtul_p(mem_buf);
-        env->vregs[n][1].ll = ldtul_p(mem_buf + 8);
+        env->vregs[n][0] = ldtul_p(mem_buf);
+        env->vregs[n][1] = ldtul_p(mem_buf + 8);
         return 16;
     default:
         return 0;
diff --git a/target/s390x/gen-features.c b/target/s390x/gen-features.c
index c346b76bdf..dc320a06c2 100644
--- a/target/s390x/gen-features.c
+++ b/target/s390x/gen-features.c
@@ -689,7 +689,7 @@ static uint16_t qemu_V3_1[] = {
     S390_FEAT_MSA_EXT_4,
 };
 
-static uint16_t qemu_LATEST[] = {
+static uint16_t qemu_V4_0[] = {
     /*
      * Only BFP bits are implemented (HFP, DFP, PFPO and DIVIDE TO INTEGER not
      * implemented yet).
@@ -698,10 +698,13 @@ static uint16_t qemu_LATEST[] = {
     S390_FEAT_ZPCI,
 };
 
+static uint16_t qemu_LATEST[] = {
+    S390_FEAT_STFLE_53,
+    S390_FEAT_VECTOR,
+};
+
 /* add all new definitions before this point */
 static uint16_t qemu_MAX[] = {
-    /* z13+ features */
-    S390_FEAT_STFLE_53,
     /* generates a dependency warning, leave it out for now */
     S390_FEAT_MSA_EXT_5,
 };
@@ -820,6 +823,7 @@ static FeatGroupDefSpec FeatGroupDef[] = {
 static FeatGroupDefSpec QemuFeatDef[] = {
     QEMU_FEAT_INITIALIZER(V2_11),
     QEMU_FEAT_INITIALIZER(V3_1),
+    QEMU_FEAT_INITIALIZER(V4_0),
     QEMU_FEAT_INITIALIZER(LATEST),
     QEMU_FEAT_INITIALIZER(MAX),
 };
diff --git a/target/s390x/helper.c b/target/s390x/helper.c
index 3c8f0a7615..a69e5abf5f 100644
--- a/target/s390x/helper.c
+++ b/target/s390x/helper.c
@@ -249,7 +249,7 @@ int s390_store_status(S390CPU *cpu, hwaddr addr, bool store_arch)
         cpu_physical_memory_write(offsetof(LowCore, ar_access_id), &ar_id, 1);
     }
     for (i = 0; i < 16; ++i) {
-        sa->fprs[i] = cpu_to_be64(get_freg(&cpu->env, i)->ll);
+        sa->fprs[i] = cpu_to_be64(*get_freg(&cpu->env, i));
     }
     for (i = 0; i < 16; ++i) {
         sa->grs[i] = cpu_to_be64(cpu->env.regs[i]);
@@ -299,8 +299,8 @@ int s390_store_adtl_status(S390CPU *cpu, hwaddr addr, hwaddr len)
 
     if (s390_has_feat(S390_FEAT_VECTOR)) {
         for (i = 0; i < 32; i++) {
-            sa->vregs[i][0] = cpu_to_be64(cpu->env.vregs[i][0].ll);
-            sa->vregs[i][1] = cpu_to_be64(cpu->env.vregs[i][1].ll);
+            sa->vregs[i][0] = cpu_to_be64(cpu->env.vregs[i][0]);
+            sa->vregs[i][1] = cpu_to_be64(cpu->env.vregs[i][1]);
         }
     }
     if (s390_has_feat(S390_FEAT_GUARDED_STORAGE) && len >= ADTL_GS_MIN_SIZE) {
@@ -341,13 +341,13 @@ void s390_cpu_dump_state(CPUState *cs, FILE *f, int flags)
         if (s390_has_feat(S390_FEAT_VECTOR)) {
             for (i = 0; i < 32; i++) {
                 qemu_fprintf(f, "V%02d=%016" PRIx64 "%016" PRIx64 "%c",
-                             i, env->vregs[i][0].ll, env->vregs[i][1].ll,
+                             i, env->vregs[i][0], env->vregs[i][1],
                              i % 2 ? '\n' : ' ');
             }
         } else {
             for (i = 0; i < 16; i++) {
                 qemu_fprintf(f, "F%02d=%016" PRIx64 "%c",
-                             i, get_freg(env, i)->ll,
+                             i, *get_freg(env, i),
                              (i % 4) == 3 ? '\n' : ' ');
             }
         }
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 7755a96c33..e9aff83b05 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -211,6 +211,90 @@ DEF_HELPER_FLAGS_4(gvec_vscbi8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_4(gvec_vtm, void, ptr, cptr, env, i32)
 
+/* === Vector String Instructions === */
+DEF_HELPER_FLAGS_4(gvec_vfae8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfae16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfae32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_5(gvec_vfae_cc8, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfae_cc16, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfae_cc32, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfee32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_5(gvec_vfee_cc8, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfee_cc16, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfee_cc32, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfene8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfene16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfene32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_5(gvec_vfene_cc8, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfene_cc16, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfene_cc32, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_3(gvec_vistr8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vistr16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vistr32, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_4(gvec_vistr_cc8, void, ptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vistr_cc16, void, ptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vistr_cc32, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc_rt8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc_rt16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vstrc_rt32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_6(gvec_vstrc_cc8, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrc_cc16, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrc_cc32, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrc_cc_rt8, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrc_cc_rt16, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
+
+/* === Vector Floating-Point Instructions */
+DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfa64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce64s_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch64s_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche64s_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdlg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfm64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfs64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
+DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
+
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
 DEF_HELPER_4(diag, void, env, i32, i32, i32)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index e61475bdc4..f421184fcd 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1191,6 +1191,64 @@
 /* VECTOR TEST UNDER MASK */
     F(0xe7d8, VTM,     VRR_a, V,   0, 0, 0, 0, vtm, 0, IF_VEC)
 
+/* === Vector String Instructions === */
+
+/* VECTOR FIND ANY ELEMENT EQUAL */
+    F(0xe782, VFAE,    VRR_b, V,   0, 0, 0, 0, vfae, 0, IF_VEC)
+/* VECTOR FIND ELEMENT EQUAL */
+    F(0xe780, VFEE,    VRR_b, V,   0, 0, 0, 0, vfee, 0, IF_VEC)
+/* VECTOR FIND ELEMENT NOT EQUAL */
+    F(0xe781, VFENE,   VRR_b, V,   0, 0, 0, 0, vfene, 0, IF_VEC)
+/* VECTOR ISOLATE STRING */
+    F(0xe75c, VISTR,   VRR_a, V,   0, 0, 0, 0, vistr, 0, IF_VEC)
+/* VECTOR STRING RANGE COMPARE */
+    F(0xe78a, VSTRC,   VRR_d, V,   0, 0, 0, 0, vstrc, 0, IF_VEC)
+
+/* === Vector Floating-Point Instructions */
+
+/* VECTOR FP ADD */
+    F(0xe7e3, VFA,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR FP COMPARE SCALAR */
+    F(0xe7cb, WFC,     VRR_a, V,   0, 0, 0, 0, wfc, 0, IF_VEC)
+/* VECTOR FP COMPARE AND SIGNAL SCALAR */
+    F(0xe7ca, WFK,     VRR_a, V,   0, 0, 0, 0, wfc, 0, IF_VEC)
+/* VECTOR FP COMPARE EQUAL */
+    F(0xe7e8, VFCE,    VRR_c, V,   0, 0, 0, 0, vfc, 0, IF_VEC)
+/* VECTOR FP COMPARE HIGH */
+    F(0xe7eb, VFCH,    VRR_c, V,   0, 0, 0, 0, vfc, 0, IF_VEC)
+/* VECTOR FP COMPARE HIGH OR EQUAL */
+    F(0xe7ea, VFCHE,   VRR_c, V,   0, 0, 0, 0, vfc, 0, IF_VEC)
+/* VECTOR FP CONVERT FROM FIXED 64-BIT */
+    F(0xe7c3, VCDG,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP CONVERT FROM LOGICAL 64-BIT */
+    F(0xe7c1, VCDLG,   VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP CONVERT TO FIXED 64-BIT */
+    F(0xe7c2, VCGD,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP CONVERT TO LOGICAL 64-BIT */
+    F(0xe7c0, VCLGD,   VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP DIVIDE */
+    F(0xe7e5, VFD,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR LOAD FP INTEGER */
+    F(0xe7c7, VFI,     VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR LOAD LENGTHENED */
+    F(0xe7c4, VFLL,    VRR_a, V,   0, 0, 0, 0, vfll, 0, IF_VEC)
+/* VECTOR LOAD ROUNDED */
+    F(0xe7c5, VFLR,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR FP MULTIPLY */
+    F(0xe7e7, VFM,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND ADD */
+    F(0xe78f, VFMA,    VRR_e, V,   0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND SUBTRACT */
+    F(0xe78e, VFMS,    VRR_e, V,   0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP PERFORM SIGN OPERATION */
+    F(0xe7cc, VFPSO,   VRR_a, V,   0, 0, 0, 0, vfpso, 0, IF_VEC)
+/* VECTOR FP SQUARE ROOT */
+    F(0xe7ce, VFSQ,    VRR_a, V,   0, 0, 0, 0, vfsq, 0, IF_VEC)
+/* VECTOR FP SUBTRACT */
+    F(0xe7e2, VFS,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR FP TEST DATA CLASS IMMEDIATE */
+    F(0xe74a, VFTCI,   VRI_e, V,   0, 0, 0, 0, vftci, 0, IF_VEC)
+
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */
     E(0xb250, CSP,     RRE,   Z,   r1_32u, ra2, r1_P, 0, csp, 0, MO_TEUL, IF_PRIV)
diff --git a/target/s390x/internal.h b/target/s390x/internal.h
index 9893fc094b..c243fa725b 100644
--- a/target/s390x/internal.h
+++ b/target/s390x/internal.h
@@ -285,6 +285,10 @@ uint32_t set_cc_nz_f128(float128 v);
 uint8_t s390_softfloat_exc_to_ieee(unsigned int exc);
 int s390_swap_bfp_rounding_mode(CPUS390XState *env, int m3);
 void s390_restore_bfp_rounding_mode(CPUS390XState *env, int old_mode);
+int float_comp_to_cc(CPUS390XState *env, int float_compare);
+uint16_t float32_dcmask(CPUS390XState *env, float32 f1);
+uint16_t float64_dcmask(CPUS390XState *env, float64 f1);
+uint16_t float128_dcmask(CPUS390XState *env, float128 f1);
 
 
 /* gdbstub.c */
diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c
index e5e2b691f2..bcec9795ec 100644
--- a/target/s390x/kvm.c
+++ b/target/s390x/kvm.c
@@ -418,21 +418,21 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
     if (can_sync_regs(cs, KVM_SYNC_VRS)) {
         for (i = 0; i < 32; i++) {
-            cs->kvm_run->s.regs.vrs[i][0] = env->vregs[i][0].ll;
-            cs->kvm_run->s.regs.vrs[i][1] = env->vregs[i][1].ll;
+            cs->kvm_run->s.regs.vrs[i][0] = env->vregs[i][0];
+            cs->kvm_run->s.regs.vrs[i][1] = env->vregs[i][1];
         }
         cs->kvm_run->s.regs.fpc = env->fpc;
         cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_VRS;
     } else if (can_sync_regs(cs, KVM_SYNC_FPRS)) {
         for (i = 0; i < 16; i++) {
-            cs->kvm_run->s.regs.fprs[i] = get_freg(env, i)->ll;
+            cs->kvm_run->s.regs.fprs[i] = *get_freg(env, i);
         }
         cs->kvm_run->s.regs.fpc = env->fpc;
         cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_FPRS;
     } else {
         /* Floating point */
         for (i = 0; i < 16; i++) {
-            fpu.fprs[i] = get_freg(env, i)->ll;
+            fpu.fprs[i] = *get_freg(env, i);
         }
         fpu.fpc = env->fpc;
 
@@ -586,13 +586,13 @@ int kvm_arch_get_registers(CPUState *cs)
     /* Floating point and vector registers */
     if (can_sync_regs(cs, KVM_SYNC_VRS)) {
         for (i = 0; i < 32; i++) {
-            env->vregs[i][0].ll = cs->kvm_run->s.regs.vrs[i][0];
-            env->vregs[i][1].ll = cs->kvm_run->s.regs.vrs[i][1];
+            env->vregs[i][0] = cs->kvm_run->s.regs.vrs[i][0];
+            env->vregs[i][1] = cs->kvm_run->s.regs.vrs[i][1];
         }
         env->fpc = cs->kvm_run->s.regs.fpc;
     } else if (can_sync_regs(cs, KVM_SYNC_FPRS)) {
         for (i = 0; i < 16; i++) {
-            get_freg(env, i)->ll = cs->kvm_run->s.regs.fprs[i];
+            *get_freg(env, i) = cs->kvm_run->s.regs.fprs[i];
         }
         env->fpc = cs->kvm_run->s.regs.fpc;
     } else {
@@ -601,7 +601,7 @@ int kvm_arch_get_registers(CPUState *cs)
             return r;
         }
         for (i = 0; i < 16; i++) {
-            get_freg(env, i)->ll = fpu.fprs[i];
+            *get_freg(env, i) = fpu.fprs[i];
         }
         env->fpc = fpu.fpc;
     }
diff --git a/target/s390x/machine.c b/target/s390x/machine.c
index cb792aa103..e6851a57bc 100644
--- a/target/s390x/machine.c
+++ b/target/s390x/machine.c
@@ -66,22 +66,22 @@ static const VMStateDescription vmstate_fpu = {
     .minimum_version_id = 1,
     .needed = fpu_needed,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(env.vregs[0][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[1][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[2][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[3][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[4][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[5][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[6][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[7][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[8][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[9][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[10][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[11][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[12][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[13][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[14][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[15][0].ll, S390CPU),
+        VMSTATE_UINT64(env.vregs[0][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[1][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[2][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[3][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[4][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[5][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[6][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[7][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[8][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[9][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[10][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[11][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[12][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[13][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[14][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[15][0], S390CPU),
         VMSTATE_UINT32(env.fpc, S390CPU),
         VMSTATE_END_OF_LIST()
     }
@@ -99,54 +99,54 @@ static const VMStateDescription vmstate_vregs = {
     .needed = vregs_needed,
     .fields = (VMStateField[]) {
         /* vregs[0][0] -> vregs[15][0] and fregs are overlays */
-        VMSTATE_UINT64(env.vregs[16][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[17][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[18][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[19][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[20][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[21][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[22][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[23][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[24][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[25][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[26][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[27][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[28][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[29][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[30][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[31][0].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[0][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[1][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[2][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[3][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[4][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[5][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[6][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[7][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[8][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[9][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[10][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[11][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[12][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[13][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[14][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[15][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[16][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[17][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[18][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[19][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[20][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[21][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[22][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[23][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[24][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[25][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[26][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[27][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[28][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[29][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[30][1].ll, S390CPU),
-        VMSTATE_UINT64(env.vregs[31][1].ll, S390CPU),
+        VMSTATE_UINT64(env.vregs[16][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[17][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[18][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[19][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[20][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[21][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[22][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[23][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[24][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[25][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[26][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[27][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[28][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[29][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[30][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[31][0], S390CPU),
+        VMSTATE_UINT64(env.vregs[0][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[1][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[2][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[3][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[4][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[5][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[6][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[7][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[8][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[9][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[10][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[11][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[12][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[13][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[14][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[15][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[16][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[17][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[18][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[19][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[20][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[21][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[22][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[23][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[24][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[25][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[26][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[27][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[28][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[29][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[30][1], S390CPU),
+        VMSTATE_UINT64(env.vregs[31][1], S390CPU),
         VMSTATE_END_OF_LIST()
     }
 };
diff --git a/target/s390x/misc_helper.c b/target/s390x/misc_helper.c
index ee67c1fa0c..10aa617cf9 100644
--- a/target/s390x/misc_helper.c
+++ b/target/s390x/misc_helper.c
@@ -669,7 +669,7 @@ uint32_t HELPER(stfle)(CPUS390XState *env, uint64_t addr)
 {
     const uintptr_t ra = GETPC();
     const int count_bytes = ((env->regs[0] & 0xff) + 1) * 8;
-    const int max_bytes = ROUND_UP(used_stfl_bytes, 8);
+    int max_bytes;
     int i;
 
     if (addr & 0x7) {
@@ -677,7 +677,14 @@ uint32_t HELPER(stfle)(CPUS390XState *env, uint64_t addr)
     }
 
     prepare_stfl();
-    for (i = 0; i < count_bytes; ++i) {
+    max_bytes = ROUND_UP(used_stfl_bytes, 8);
+
+    /*
+     * The PoP says that doublewords beyond the highest-numbered facility
+     * bit may or may not be stored.  However, existing hardware appears to
+     * not store the words, and existing software depend on that.
+     */
+    for (i = 0; i < MIN(count_bytes, max_bytes); ++i) {
         cpu_stb_data_ra(env, addr + i, stfl_bytes[i], ra);
     }
 
diff --git a/target/s390x/tcg_s390x.h b/target/s390x/tcg_s390x.h
index ab2c4ba703..2813f9d48e 100644
--- a/target/s390x/tcg_s390x.h
+++ b/target/s390x/tcg_s390x.h
@@ -18,5 +18,7 @@ void QEMU_NORETURN tcg_s390_program_interrupt(CPUS390XState *env, uint32_t code,
                                               int ilen, uintptr_t ra);
 void QEMU_NORETURN tcg_s390_data_exception(CPUS390XState *env, uint32_t dxc,
                                            uintptr_t ra);
+void QEMU_NORETURN tcg_s390_vector_exception(CPUS390XState *env, uint32_t vxc,
+                                             uintptr_t ra);
 
 #endif /* TCG_S390X_H */
diff --git a/target/s390x/translate.c b/target/s390x/translate.c
index fa57b7550e..ac0d8b6410 100644
--- a/target/s390x/translate.c
+++ b/target/s390x/translate.c
@@ -149,7 +149,7 @@ void s390x_translate_init(void)
 static inline int vec_full_reg_offset(uint8_t reg)
 {
     g_assert(reg < 32);
-    return offsetof(CPUS390XState, vregs[reg][0].d);
+    return offsetof(CPUS390XState, vregs[reg][0]);
 }
 
 static inline int vec_reg_offset(uint8_t reg, uint8_t enr, TCGMemOp es)
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 7e0bfcb190..7b1d31cba5 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -52,6 +52,11 @@
 #define ES_64   MO_64
 #define ES_128  4
 
+/* Floating-Point Format */
+#define FPF_SHORT       2
+#define FPF_LONG        3
+#define FPF_EXT         4
+
 static inline bool valid_vec_element(uint8_t enr, TCGMemOp es)
 {
     return !(enr & ~(NUM_VEC_ELEMENTS(es) - 1));
@@ -188,6 +193,9 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
 #define gen_gvec_2s(v1, v2, c, gen) \
     tcg_gen_gvec_2s(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                     16, 16, c, gen)
+#define gen_gvec_2_ool(v1, v2, data, fn) \
+    tcg_gen_gvec_2_ool(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                       16, 16, data, fn)
 #define gen_gvec_2i_ool(v1, v2, c, data, fn) \
     tcg_gen_gvec_2i_ool(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                         c, 16, 16, data, fn)
@@ -214,6 +222,10 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
     tcg_gen_gvec_4_ool(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                        vec_full_reg_offset(v3), vec_full_reg_offset(v4), \
                        16, 16, data, fn)
+#define gen_gvec_4_ptr(v1, v2, v3, v4, ptr, data, fn) \
+    tcg_gen_gvec_4_ptr(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                       vec_full_reg_offset(v3), vec_full_reg_offset(v4), \
+                       ptr, 16, 16, data, fn)
 #define gen_gvec_dup_i64(es, v1, c) \
     tcg_gen_gvec_dup_i64(es, vec_full_reg_offset(v1), 16, 16, c)
 #define gen_gvec_mov(v1, v2) \
@@ -233,6 +245,9 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
 #define gen_gvec_fn_3(fn, es, v1, v2, v3) \
     tcg_gen_gvec_##fn(es, vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                       vec_full_reg_offset(v3), 16, 16)
+#define gen_gvec_fn_4(fn, es, v1, v2, v3, v4) \
+    tcg_gen_gvec_##fn(es, vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                      vec_full_reg_offset(v3), vec_full_reg_offset(v4), 16, 16)
 
 /*
  * Helper to carry out a 128 bit vector computation using 2 i64 values per
@@ -903,40 +918,11 @@ static DisasJumpType op_vsce(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
-static void gen_sel_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b, TCGv_i64 c)
-{
-    TCGv_i64 t = tcg_temp_new_i64();
-
-    /* bit in c not set -> copy bit from b */
-    tcg_gen_andc_i64(t, b, c);
-    /* bit in c set -> copy bit from a */
-    tcg_gen_and_i64(d, a, c);
-    /* merge the results */
-    tcg_gen_or_i64(d, d, t);
-    tcg_temp_free_i64(t);
-}
-
-static void gen_sel_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b,
-                        TCGv_vec c)
-{
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
-
-    tcg_gen_andc_vec(vece, t, b, c);
-    tcg_gen_and_vec(vece, d, a, c);
-    tcg_gen_or_vec(vece, d, d, t);
-    tcg_temp_free_vec(t);
-}
-
 static DisasJumpType op_vsel(DisasContext *s, DisasOps *o)
 {
-    static const GVecGen4 gvec_op = {
-        .fni8 = gen_sel_i64,
-        .fniv = gen_sel_vec,
-        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-    };
-
-    gen_gvec_4(get_field(s->fields, v1), get_field(s->fields, v2),
-               get_field(s->fields, v3), get_field(s->fields, v4), &gvec_op);
+    gen_gvec_fn_4(bitsel, ES_8, get_field(s->fields, v1),
+                  get_field(s->fields, v4), get_field(s->fields, v2),
+                  get_field(s->fields, v3));
     return DISAS_NEXT;
 }
 
@@ -2353,3 +2339,460 @@ static DisasJumpType op_vtm(DisasContext *s, DisasOps *o)
     set_cc_static(s);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vfae(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_3 * const g[3] = {
+        gen_helper_gvec_vfae8,
+        gen_helper_gvec_vfae16,
+        gen_helper_gvec_vfae32,
+    };
+    static gen_helper_gvec_3_ptr * const g_cc[3] = {
+        gen_helper_gvec_vfae_cc8,
+        gen_helper_gvec_vfae_cc16,
+        gen_helper_gvec_vfae_cc32,
+    };
+    if (es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), cpu_env, m5, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), m5, g[es]);
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfee(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_3 * const g[3] = {
+        gen_helper_gvec_vfee8,
+        gen_helper_gvec_vfee16,
+        gen_helper_gvec_vfee32,
+    };
+    static gen_helper_gvec_3_ptr * const g_cc[3] = {
+        gen_helper_gvec_vfee_cc8,
+        gen_helper_gvec_vfee_cc16,
+        gen_helper_gvec_vfee_cc32,
+    };
+
+    if (es > ES_32 || m5 & ~0x3) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), cpu_env, m5, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), m5, g[es]);
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfene(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_3 * const g[3] = {
+        gen_helper_gvec_vfene8,
+        gen_helper_gvec_vfene16,
+        gen_helper_gvec_vfene32,
+    };
+    static gen_helper_gvec_3_ptr * const g_cc[3] = {
+        gen_helper_gvec_vfene_cc8,
+        gen_helper_gvec_vfene_cc16,
+        gen_helper_gvec_vfene_cc32,
+    };
+
+    if (es > ES_32 || m5 & ~0x3) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), cpu_env, m5, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), m5, g[es]);
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vistr(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_2 * const g[3] = {
+        gen_helper_gvec_vistr8,
+        gen_helper_gvec_vistr16,
+        gen_helper_gvec_vistr32,
+    };
+    static gen_helper_gvec_2_ptr * const g_cc[3] = {
+        gen_helper_gvec_vistr_cc8,
+        gen_helper_gvec_vistr_cc16,
+        gen_helper_gvec_vistr_cc32,
+    };
+
+    if (es > ES_32 || m5 & ~0x1) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       cpu_env, 0, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_2_ool(get_field(s->fields, v1), get_field(s->fields, v2), 0,
+                       g[es]);
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vstrc(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m5);
+    const uint8_t m6 = get_field(s->fields, m6);
+    static gen_helper_gvec_4 * const g[3] = {
+        gen_helper_gvec_vstrc8,
+        gen_helper_gvec_vstrc16,
+        gen_helper_gvec_vstrc32,
+    };
+    static gen_helper_gvec_4 * const g_rt[3] = {
+        gen_helper_gvec_vstrc_rt8,
+        gen_helper_gvec_vstrc_rt16,
+        gen_helper_gvec_vstrc_rt32,
+    };
+    static gen_helper_gvec_4_ptr * const g_cc[3] = {
+        gen_helper_gvec_vstrc_cc8,
+        gen_helper_gvec_vstrc_cc16,
+        gen_helper_gvec_vstrc_cc32,
+    };
+    static gen_helper_gvec_4_ptr * const g_cc_rt[3] = {
+        gen_helper_gvec_vstrc_cc_rt8,
+        gen_helper_gvec_vstrc_cc_rt16,
+        gen_helper_gvec_vstrc_cc_rt32,
+    };
+
+    if (es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m6, 0, 1)) {
+        if (extract32(m6, 2, 1)) {
+            gen_gvec_4_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                           get_field(s->fields, v3), get_field(s->fields, v4),
+                           cpu_env, m6, g_cc_rt[es]);
+        } else {
+            gen_gvec_4_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                           get_field(s->fields, v3), get_field(s->fields, v4),
+                           cpu_env, m6, g_cc[es]);
+        }
+        set_cc_static(s);
+    } else {
+        if (extract32(m6, 2, 1)) {
+            gen_gvec_4_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                           get_field(s->fields, v3), get_field(s->fields, v4),
+                           m6, g_rt[es]);
+        } else {
+            gen_gvec_4_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                           get_field(s->fields, v3), get_field(s->fields, v4),
+                           m6, g[es]);
+        }
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    const bool se = extract32(m5, 3, 1);
+    gen_helper_gvec_3_ptr *fn;
+
+    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    switch (s->fields->op2) {
+    case 0xe3:
+        fn = se ? gen_helper_gvec_vfa64s : gen_helper_gvec_vfa64;
+        break;
+    case 0xe5:
+        fn = se ? gen_helper_gvec_vfd64s : gen_helper_gvec_vfd64;
+        break;
+    case 0xe7:
+        fn = se ? gen_helper_gvec_vfm64s : gen_helper_gvec_vfm64;
+        break;
+    case 0xe2:
+        fn = se ? gen_helper_gvec_vfs64s : gen_helper_gvec_vfs64;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                   get_field(s->fields, v3), cpu_env, 0, fn);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_wfc(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+
+    if (fpf != FPF_LONG || m4) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (s->fields->op2 == 0xcb) {
+        gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       cpu_env, 0, gen_helper_gvec_wfc64);
+    } else {
+        gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       cpu_env, 0, gen_helper_gvec_wfk64);
+    }
+    set_cc_static(s);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfc(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    const uint8_t m6 = get_field(s->fields, m6);
+    const bool se = extract32(m5, 3, 1);
+    const bool cs = extract32(m6, 0, 1);
+    gen_helper_gvec_3_ptr *fn;
+
+    if (fpf != FPF_LONG || extract32(m5, 0, 3) || extract32(m6, 1, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (cs) {
+        switch (s->fields->op2) {
+        case 0xe8:
+            fn = se ? gen_helper_gvec_vfce64s_cc : gen_helper_gvec_vfce64_cc;
+            break;
+        case 0xeb:
+            fn = se ? gen_helper_gvec_vfch64s_cc : gen_helper_gvec_vfch64_cc;
+            break;
+        case 0xea:
+            fn = se ? gen_helper_gvec_vfche64s_cc : gen_helper_gvec_vfche64_cc;
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    } else {
+        switch (s->fields->op2) {
+        case 0xe8:
+            fn = se ? gen_helper_gvec_vfce64s : gen_helper_gvec_vfce64;
+            break;
+        case 0xeb:
+            fn = se ? gen_helper_gvec_vfch64s : gen_helper_gvec_vfch64;
+            break;
+        case 0xea:
+            fn = se ? gen_helper_gvec_vfche64s : gen_helper_gvec_vfche64;
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    }
+    gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                   get_field(s->fields, v3), cpu_env, 0, fn);
+    if (cs) {
+        set_cc_static(s);
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+    const uint8_t erm = get_field(s->fields, m5);
+    const bool se = extract32(m4, 3, 1);
+    gen_helper_gvec_2_ptr *fn;
+
+    if (fpf != FPF_LONG || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    switch (s->fields->op2) {
+    case 0xc3:
+        fn = se ? gen_helper_gvec_vcdg64s : gen_helper_gvec_vcdg64;
+        break;
+    case 0xc1:
+        fn = se ? gen_helper_gvec_vcdlg64s : gen_helper_gvec_vcdlg64;
+        break;
+    case 0xc2:
+        fn = se ? gen_helper_gvec_vcgd64s : gen_helper_gvec_vcgd64;
+        break;
+    case 0xc0:
+        fn = se ? gen_helper_gvec_vclgd64s : gen_helper_gvec_vclgd64;
+        break;
+    case 0xc7:
+        fn = se ? gen_helper_gvec_vfi64s : gen_helper_gvec_vfi64;
+        break;
+    case 0xc5:
+        fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2), cpu_env,
+                   deposit32(m4, 4, 4, erm), fn);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfll32;
+
+    if (fpf != FPF_SHORT || extract32(m4, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m4, 3, 1)) {
+        fn = gen_helper_gvec_vfll32s;
+    }
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2), cpu_env,
+                   0, fn);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
+{
+    const uint8_t m5 = get_field(s->fields, m5);
+    const uint8_t fpf = get_field(s->fields, m6);
+    const bool se = extract32(m5, 3, 1);
+    gen_helper_gvec_4_ptr *fn;
+
+    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (s->fields->op2 == 0x8f) {
+        fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64;
+    } else {
+        fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64;
+    }
+    gen_gvec_4_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                   get_field(s->fields, v3), get_field(s->fields, v4), cpu_env,
+                   0, fn);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfpso(DisasContext *s, DisasOps *o)
+{
+    const uint8_t v1 = get_field(s->fields, v1);
+    const uint8_t v2 = get_field(s->fields, v2);
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    TCGv_i64 tmp;
+
+    if (fpf != FPF_LONG || extract32(m4, 0, 3) || m5 > 2) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m4, 3, 1)) {
+        tmp = tcg_temp_new_i64();
+        read_vec_element_i64(tmp, v2, 0, ES_64);
+        switch (m5) {
+        case 0:
+            /* sign bit is inverted (complement) */
+            tcg_gen_xori_i64(tmp, tmp, 1ull << 63);
+            break;
+        case 1:
+            /* sign bit is set to one (negative) */
+            tcg_gen_ori_i64(tmp, tmp, 1ull << 63);
+            break;
+        case 2:
+            /* sign bit is set to zero (positive) */
+            tcg_gen_andi_i64(tmp, tmp, (1ull << 63) - 1);
+            break;
+        }
+        write_vec_element_i64(tmp, v1, 0, ES_64);
+        tcg_temp_free_i64(tmp);
+    } else {
+        switch (m5) {
+        case 0:
+            /* sign bit is inverted (complement) */
+            gen_gvec_fn_2i(xori, ES_64, v1, v2, 1ull << 63);
+            break;
+        case 1:
+            /* sign bit is set to one (negative) */
+            gen_gvec_fn_2i(ori, ES_64, v1, v2, 1ull << 63);
+            break;
+        case 2:
+            /* sign bit is set to zero (positive) */
+            gen_gvec_fn_2i(andi, ES_64, v1, v2, (1ull << 63) - 1);
+            break;
+        }
+    }
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfsq64;
+
+    if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m4, 3, 1)) {
+        fn = gen_helper_gvec_vfsq64s;
+    }
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2), cpu_env,
+                   0, fn);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vftci(DisasContext *s, DisasOps *o)
+{
+    const uint16_t i3 = get_field(s->fields, i3);
+    const uint8_t fpf = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vftci64;
+
+    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 3, 1)) {
+        fn = gen_helper_gvec_vftci64s;
+    }
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2), cpu_env,
+                   i3, fn);
+    set_cc_static(s);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec.h b/target/s390x/vec.h
index 3313fb43ee..a6e361869b 100644
--- a/target/s390x/vec.h
+++ b/target/s390x/vec.h
@@ -12,6 +12,8 @@
 #ifndef S390X_VEC_H
 #define S390X_VEC_H
 
+#include "tcg/tcg.h"
+
 typedef union S390Vector {
     uint64_t doubleword[2];
     uint32_t word[4];
@@ -70,6 +72,23 @@ static inline uint64_t s390_vec_read_element64(const S390Vector *v, uint8_t enr)
     return v->doubleword[enr];
 }
 
+static inline uint64_t s390_vec_read_element(const S390Vector *v, uint8_t enr,
+                                             uint8_t es)
+{
+    switch (es) {
+    case MO_8:
+        return s390_vec_read_element8(v, enr);
+    case MO_16:
+        return s390_vec_read_element16(v, enr);
+    case MO_32:
+        return s390_vec_read_element32(v, enr);
+    case MO_64:
+        return s390_vec_read_element64(v, enr);
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static inline void s390_vec_write_element8(S390Vector *v, uint8_t enr,
                                            uint8_t data)
 {
@@ -98,4 +117,25 @@ static inline void s390_vec_write_element64(S390Vector *v, uint8_t enr,
     v->doubleword[enr] = data;
 }
 
+static inline void s390_vec_write_element(S390Vector *v, uint8_t enr,
+                                          uint8_t es, uint64_t data)
+{
+    switch (es) {
+    case MO_8:
+        s390_vec_write_element8(v, enr, data);
+        break;
+    case MO_16:
+        s390_vec_write_element16(v, enr, data);
+        break;
+    case MO_32:
+        s390_vec_write_element32(v, enr, data);
+        break;
+    case MO_64:
+        s390_vec_write_element64(v, enr, data);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 #endif /* S390X_VEC_H */
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
new file mode 100644
index 0000000000..a48bd704bc
--- /dev/null
+++ b/target/s390x/vec_fpu_helper.c
@@ -0,0 +1,625 @@
+/*
+ * QEMU TCG support -- s390x vector floating point instruction support
+ *
+ * Copyright (C) 2019 Red Hat Inc
+ *
+ * Authors:
+ *   David Hildenbrand <david@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "cpu.h"
+#include "internal.h"
+#include "vec.h"
+#include "tcg_s390x.h"
+#include "tcg/tcg-gvec-desc.h"
+#include "exec/exec-all.h"
+#include "exec/helper-proto.h"
+#include "fpu/softfloat.h"
+
+#define VIC_INVALID         0x1
+#define VIC_DIVBYZERO       0x2
+#define VIC_OVERFLOW        0x3
+#define VIC_UNDERFLOW       0x4
+#define VIC_INEXACT         0x5
+
+/* returns the VEX. If the VEX is 0, there is no trap */
+static uint8_t check_ieee_exc(CPUS390XState *env, uint8_t enr, bool XxC,
+                              uint8_t *vec_exc)
+{
+    uint8_t vece_exc = 0, trap_exc;
+    unsigned qemu_exc;
+
+    /* Retrieve and clear the softfloat exceptions */
+    qemu_exc = env->fpu_status.float_exception_flags;
+    if (qemu_exc == 0) {
+        return 0;
+    }
+    env->fpu_status.float_exception_flags = 0;
+
+    vece_exc = s390_softfloat_exc_to_ieee(qemu_exc);
+
+    /* Add them to the vector-wide s390x exception bits */
+    *vec_exc |= vece_exc;
+
+    /* Check for traps and construct the VXC */
+    trap_exc = vece_exc & env->fpc >> 24;
+    if (trap_exc) {
+        if (trap_exc & S390_IEEE_MASK_INVALID) {
+            return enr << 4 | VIC_INVALID;
+        } else if (trap_exc & S390_IEEE_MASK_DIVBYZERO) {
+            return enr << 4 | VIC_DIVBYZERO;
+        } else if (trap_exc & S390_IEEE_MASK_OVERFLOW) {
+            return enr << 4 | VIC_OVERFLOW;
+        } else if (trap_exc & S390_IEEE_MASK_UNDERFLOW) {
+            return enr << 4 | VIC_UNDERFLOW;
+        } else if (!XxC) {
+            g_assert(trap_exc & S390_IEEE_MASK_INEXACT);
+            /* inexact has lowest priority on traps */
+            return enr << 4 | VIC_INEXACT;
+        }
+    }
+    return 0;
+}
+
+static void handle_ieee_exc(CPUS390XState *env, uint8_t vxc, uint8_t vec_exc,
+                            uintptr_t retaddr)
+{
+    if (vxc) {
+        /* on traps, the fpc flags are not updated, instruction is suppressed */
+        tcg_s390_vector_exception(env, vxc, retaddr);
+    }
+    if (vec_exc) {
+        /* indicate exceptions for all elements combined */
+        env->fpc |= vec_exc << 16;
+    }
+}
+
+typedef uint64_t (*vop64_2_fn)(uint64_t a, float_status *s);
+static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                    bool s, bool XxC, uint8_t erm, vop64_2_fn fn,
+                    uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i, old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    for (i = 0; i < 2; i++) {
+        const uint64_t a = s390_vec_read_element64(v2, i);
+
+        s390_vec_write_element64(&tmp, i, fn(a, &env->fpu_status));
+        vxc = check_ieee_exc(env, i, XxC, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+typedef uint64_t (*vop64_3_fn)(uint64_t a, uint64_t b, float_status *s);
+static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                    CPUS390XState *env, bool s, vop64_3_fn fn,
+                    uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        const uint64_t a = s390_vec_read_element64(v2, i);
+        const uint64_t b = s390_vec_read_element64(v3, i);
+
+        s390_vec_write_element64(&tmp, i, fn(a, b, &env->fpu_status));
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+static uint64_t vfa64(uint64_t a, uint64_t b, float_status *s)
+{
+    return float64_add(a, b, s);
+}
+
+void HELPER(gvec_vfa64)(void *v1, const void *v2, const void *v3,
+                        CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, false, vfa64, GETPC());
+}
+
+void HELPER(gvec_vfa64s)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, true, vfa64, GETPC());
+}
+
+static int wfc64(const S390Vector *v1, const S390Vector *v2,
+                 CPUS390XState *env, bool signal, uintptr_t retaddr)
+{
+    /* only the zero-indexed elements are compared */
+    const float64 a = s390_vec_read_element64(v1, 0);
+    const float64 b = s390_vec_read_element64(v2, 0);
+    uint8_t vxc, vec_exc = 0;
+    int cmp;
+
+    if (signal) {
+        cmp = float64_compare(a, b, &env->fpu_status);
+    } else {
+        cmp = float64_compare_quiet(a, b, &env->fpu_status);
+    }
+    vxc = check_ieee_exc(env, 0, false, &vec_exc);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+
+    return float_comp_to_cc(env, cmp);
+}
+
+void HELPER(gvec_wfc64)(const void *v1, const void *v2, CPUS390XState *env,
+                        uint32_t desc)
+{
+    env->cc_op = wfc64(v1, v2, env, false, GETPC());
+}
+
+void HELPER(gvec_wfk64)(const void *v1, const void *v2, CPUS390XState *env,
+                        uint32_t desc)
+{
+    env->cc_op = wfc64(v1, v2, env, true, GETPC());
+}
+
+typedef int (*vfc64_fn)(float64 a, float64 b, float_status *status);
+static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                 CPUS390XState *env, bool s, vfc64_fn fn, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int match = 0;
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        const float64 a = s390_vec_read_element64(v2, i);
+        const float64 b = s390_vec_read_element64(v3, i);
+
+        /* swap the order of the parameters, so we can use existing functions */
+        if (fn(b, a, &env->fpu_status)) {
+            match++;
+            s390_vec_write_element64(&tmp, i, -1ull);
+        }
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+    if (match) {
+        return s || match == 2 ? 0 : 1;
+    }
+    return 3;
+}
+
+void HELPER(gvec_vfce64)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, false, float64_eq_quiet, GETPC());
+}
+
+void HELPER(gvec_vfce64s)(void *v1, const void *v2, const void *v3,
+                          CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, true, float64_eq_quiet, GETPC());
+}
+
+void HELPER(gvec_vfce64_cc)(void *v1, const void *v2, const void *v3,
+                            CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, false, float64_eq_quiet, GETPC());
+}
+
+void HELPER(gvec_vfce64s_cc)(void *v1, const void *v2, const void *v3,
+                            CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, true, float64_eq_quiet, GETPC());
+}
+
+void HELPER(gvec_vfch64)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, false, float64_lt_quiet, GETPC());
+}
+
+void HELPER(gvec_vfch64s)(void *v1, const void *v2, const void *v3,
+                          CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, true, float64_lt_quiet, GETPC());
+}
+
+void HELPER(gvec_vfch64_cc)(void *v1, const void *v2, const void *v3,
+                            CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, false, float64_lt_quiet, GETPC());
+}
+
+void HELPER(gvec_vfch64s_cc)(void *v1, const void *v2, const void *v3,
+                             CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, true, float64_lt_quiet, GETPC());
+}
+
+void HELPER(gvec_vfche64)(void *v1, const void *v2, const void *v3,
+                          CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, false, float64_le_quiet, GETPC());
+}
+
+void HELPER(gvec_vfche64s)(void *v1, const void *v2, const void *v3,
+                           CPUS390XState *env, uint32_t desc)
+{
+    vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC());
+}
+
+void HELPER(gvec_vfche64_cc)(void *v1, const void *v2, const void *v3,
+                             CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, false, float64_le_quiet, GETPC());
+}
+
+void HELPER(gvec_vfche64s_cc)(void *v1, const void *v2, const void *v3,
+                              CPUS390XState *env, uint32_t desc)
+{
+    env->cc_op = vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC());
+}
+
+static uint64_t vcdg64(uint64_t a, float_status *s)
+{
+    return int64_to_float64(a, s);
+}
+
+void HELPER(gvec_vcdg64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, false, XxC, erm, vcdg64, GETPC());
+}
+
+void HELPER(gvec_vcdg64s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, true, XxC, erm, vcdg64, GETPC());
+}
+
+static uint64_t vcdlg64(uint64_t a, float_status *s)
+{
+    return uint64_to_float64(a, s);
+}
+
+void HELPER(gvec_vcdlg64)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, false, XxC, erm, vcdlg64, GETPC());
+}
+
+void HELPER(gvec_vcdlg64s)(void *v1, const void *v2, CPUS390XState *env,
+                           uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, true, XxC, erm, vcdlg64, GETPC());
+}
+
+static uint64_t vcgd64(uint64_t a, float_status *s)
+{
+    return float64_to_int64(a, s);
+}
+
+void HELPER(gvec_vcgd64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, false, XxC, erm, vcgd64, GETPC());
+}
+
+void HELPER(gvec_vcgd64s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, true, XxC, erm, vcgd64, GETPC());
+}
+
+static uint64_t vclgd64(uint64_t a, float_status *s)
+{
+    return float64_to_uint64(a, s);
+}
+
+void HELPER(gvec_vclgd64)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, false, XxC, erm, vclgd64, GETPC());
+}
+
+void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env,
+                           uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC());
+}
+
+static uint64_t vfd64(uint64_t a, uint64_t b, float_status *s)
+{
+    return float64_div(a, b, s);
+}
+
+void HELPER(gvec_vfd64)(void *v1, const void *v2, const void *v3,
+                        CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, false, vfd64, GETPC());
+}
+
+void HELPER(gvec_vfd64s)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, true, vfd64, GETPC());
+}
+
+static uint64_t vfi64(uint64_t a, float_status *s)
+{
+    return float64_round_to_int(a, s);
+}
+
+void HELPER(gvec_vfi64)(void *v1, const void *v2, CPUS390XState *env,
+                        uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, false, XxC, erm, vfi64, GETPC());
+}
+
+void HELPER(gvec_vfi64s)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vop64_2(v1, v2, env, true, XxC, erm, vfi64, GETPC());
+}
+
+static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                   bool s, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        /* load from even element */
+        const float32 a = s390_vec_read_element32(v2, i * 2);
+        const uint64_t ret = float32_to_float64(a, &env->fpu_status);
+
+        s390_vec_write_element64(&tmp, i, ret);
+        /* indicate the source element */
+        vxc = check_ieee_exc(env, i * 2, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    vfll32(v1, v2, env, false, GETPC());
+}
+
+void HELPER(gvec_vfll32s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    vfll32(v1, v2, env, true, GETPC());
+}
+
+static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                   bool s, bool XxC, uint8_t erm, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i, old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    for (i = 0; i < 2; i++) {
+        float64 a = s390_vec_read_element64(v2, i);
+        uint32_t ret = float64_to_float32(a, &env->fpu_status);
+
+        /* place at even element */
+        s390_vec_write_element32(&tmp, i * 2, ret);
+        /* indicate the source element */
+        vxc = check_ieee_exc(env, i, XxC, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vflr64(v1, v2, env, false, XxC, erm, GETPC());
+}
+
+void HELPER(gvec_vflr64s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    const uint8_t erm = extract32(simd_data(desc), 4, 4);
+    const bool XxC = extract32(simd_data(desc), 2, 1);
+
+    vflr64(v1, v2, env, true, XxC, erm, GETPC());
+}
+
+static uint64_t vfm64(uint64_t a, uint64_t b, float_status *s)
+{
+    return float64_mul(a, b, s);
+}
+
+void HELPER(gvec_vfm64)(void *v1, const void *v2, const void *v3,
+                        CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, false, vfm64, GETPC());
+}
+
+void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, true, vfm64, GETPC());
+}
+
+static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                   const S390Vector *v4, CPUS390XState *env, bool s, int flags,
+                   uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        const uint64_t a = s390_vec_read_element64(v2, i);
+        const uint64_t b = s390_vec_read_element64(v3, i);
+        const uint64_t c = s390_vec_read_element64(v4, i);
+        uint64_t ret = float64_muladd(a, b, c, flags, &env->fpu_status);
+
+        s390_vec_write_element64(&tmp, i, ret);
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+void HELPER(gvec_vfma64)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vfma64(v1, v2, v3, v4, env, false, 0, GETPC());
+}
+
+void HELPER(gvec_vfma64s)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vfma64(v1, v2, v3, v4, env, true, 0, GETPC());
+}
+
+void HELPER(gvec_vfms64)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vfma64(v1, v2, v3, v4, env, false, float_muladd_negate_c, GETPC());
+}
+
+void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
+}
+
+static uint64_t vfsq64(uint64_t a, float_status *s)
+{
+    return float64_sqrt(a, s);
+}
+
+void HELPER(gvec_vfsq64)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    vop64_2(v1, v2, env, false, false, 0, vfsq64, GETPC());
+}
+
+void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    vop64_2(v1, v2, env, true, false, 0, vfsq64, GETPC());
+}
+
+static uint64_t vfs64(uint64_t a, uint64_t b, float_status *s)
+{
+    return float64_sub(a, b, s);
+}
+
+void HELPER(gvec_vfs64)(void *v1, const void *v2, const void *v3,
+                        CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, false, vfs64, GETPC());
+}
+
+void HELPER(gvec_vfs64s)(void *v1, const void *v2, const void *v3,
+                         CPUS390XState *env, uint32_t desc)
+{
+    vop64_3(v1, v2, v3, env, true, vfs64, GETPC());
+}
+
+static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                   bool s, uint16_t i3)
+{
+    int i, match = 0;
+
+    for (i = 0; i < 2; i++) {
+        float64 a = s390_vec_read_element64(v2, i);
+
+        if (float64_dcmask(env, a) & i3) {
+            match++;
+            s390_vec_write_element64(v1, i, -1ull);
+        } else {
+            s390_vec_write_element64(v1, i, 0);
+        }
+        if (s) {
+            break;
+        }
+    }
+
+    if (match) {
+        return s || match == 2 ? 0 : 1;
+    }
+    return 3;
+}
+
+void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    env->cc_op = vftci64(v1, v2, env, false, simd_data(desc));
+}
+
+void HELPER(gvec_vftci64s)(void *v1, const void *v2, CPUS390XState *env,
+                           uint32_t desc)
+{
+    env->cc_op = vftci64(v1, v2, env, true, simd_data(desc));
+}
diff --git a/target/s390x/vec_string_helper.c b/target/s390x/vec_string_helper.c
new file mode 100644
index 0000000000..c516c0ceeb
--- /dev/null
+++ b/target/s390x/vec_string_helper.c
@@ -0,0 +1,473 @@
+/*
+ * QEMU TCG support -- s390x vector string instruction support
+ *
+ * Copyright (C) 2019 Red Hat Inc
+ *
+ * Authors:
+ *   David Hildenbrand <david@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "cpu.h"
+#include "internal.h"
+#include "vec.h"
+#include "tcg/tcg.h"
+#include "tcg/tcg-gvec-desc.h"
+#include "exec/helper-proto.h"
+
+/*
+ * Returns a bit set in the MSB of each element that is zero,
+ * as defined by the mask.
+ */
+static inline uint64_t zero_search(uint64_t a, uint64_t mask)
+{
+    return ~(((a & mask) + mask) | a | mask);
+}
+
+/*
+ * Returns a bit set in the MSB of each element that is not zero,
+ * as defined by the mask.
+ */
+static inline uint64_t nonzero_search(uint64_t a, uint64_t mask)
+{
+    return (((a & mask) + mask) | a) & ~mask;
+}
+
+/*
+ * Returns the byte offset for the first match, or 16 for no match.
+ */
+static inline int match_index(uint64_t c0, uint64_t c1)
+{
+    return (c0 ? clz64(c0) : clz64(c1) + 64) >> 3;
+}
+
+/*
+ * Returns the number of bits composing one element.
+ */
+static uint8_t get_element_bits(uint8_t es)
+{
+    return (1 << es) * BITS_PER_BYTE;
+}
+
+/*
+ * Returns the bitmask for a single element.
+ */
+static uint64_t get_single_element_mask(uint8_t es)
+{
+    return -1ull >> (64 - get_element_bits(es));
+}
+
+/*
+ * Returns the bitmask for a single element (excluding the MSB).
+ */
+static uint64_t get_single_element_lsbs_mask(uint8_t es)
+{
+    return -1ull >> (65 - get_element_bits(es));
+}
+
+/*
+ * Returns the bitmasks for multiple elements (excluding the MSBs).
+ */
+static uint64_t get_element_lsbs_mask(uint8_t es)
+{
+    return dup_const(es, get_single_element_lsbs_mask(es));
+}
+
+static int vfae(void *v1, const void *v2, const void *v3, bool in,
+                bool rt, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    const int bits = get_element_bits(es);
+    uint64_t a0, a1, b0, b1, e0, e1, t0, t1, z0, z1;
+    uint64_t first_zero = 16;
+    uint64_t first_equal;
+    int i;
+
+    a0 = s390_vec_read_element64(v2, 0);
+    a1 = s390_vec_read_element64(v2, 1);
+    b0 = s390_vec_read_element64(v3, 0);
+    b1 = s390_vec_read_element64(v3, 1);
+    e0 = 0;
+    e1 = 0;
+    /* compare against equality with every other element */
+    for (i = 0; i < 64; i += bits) {
+        t0 = rol64(b0, i);
+        t1 = rol64(b1, i);
+        e0 |= zero_search(a0 ^ t0, mask);
+        e0 |= zero_search(a0 ^ t1, mask);
+        e1 |= zero_search(a1 ^ t0, mask);
+        e1 |= zero_search(a1 ^ t1, mask);
+    }
+    /* invert the result if requested - invert only the MSBs */
+    if (in) {
+        e0 = ~e0 & ~mask;
+        e1 = ~e1 & ~mask;
+    }
+    first_equal = match_index(e0, e1);
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    if (rt) {
+        e0 = (e0 >> (bits - 1)) * get_single_element_mask(es);
+        e1 = (e1 >> (bits - 1)) * get_single_element_mask(es);
+        s390_vec_write_element64(v1, 0, e0);
+        s390_vec_write_element64(v1, 1, e1);
+    } else {
+        s390_vec_write_element64(v1, 0, MIN(first_equal, first_zero));
+        s390_vec_write_element64(v1, 1, 0);
+    }
+
+    if (first_zero == 16 && first_equal == 16) {
+        return 3; /* no match */
+    } else if (first_zero == 16) {
+        return 1; /* matching elements, no match for zero */
+    } else if (first_equal < first_zero) {
+        return 2; /* matching elements before match for zero */
+    }
+    return 0; /* match for zero */
+}
+
+#define DEF_VFAE_HELPER(BITS)                                                  \
+void HELPER(gvec_vfae##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool rt = extract32(simd_data(desc), 2, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vfae(v1, v2, v3, in, rt, zs, MO_##BITS);                                   \
+}
+DEF_VFAE_HELPER(8)
+DEF_VFAE_HELPER(16)
+DEF_VFAE_HELPER(32)
+
+#define DEF_VFAE_CC_HELPER(BITS)                                               \
+void HELPER(gvec_vfae_cc##BITS)(void *v1, const void *v2, const void *v3,      \
+                                CPUS390XState *env, uint32_t desc)             \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool rt = extract32(simd_data(desc), 2, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vfae(v1, v2, v3, in, rt, zs, MO_##BITS);                      \
+}
+DEF_VFAE_CC_HELPER(8)
+DEF_VFAE_CC_HELPER(16)
+DEF_VFAE_CC_HELPER(32)
+
+static int vfee(void *v1, const void *v2, const void *v3, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    uint64_t a0, a1, b0, b1, e0, e1, z0, z1;
+    uint64_t first_zero = 16;
+    uint64_t first_equal;
+
+    a0 = s390_vec_read_element64(v2, 0);
+    a1 = s390_vec_read_element64(v2, 1);
+    b0 = s390_vec_read_element64(v3, 0);
+    b1 = s390_vec_read_element64(v3, 1);
+    e0 = zero_search(a0 ^ b0, mask);
+    e1 = zero_search(a1 ^ b1, mask);
+    first_equal = match_index(e0, e1);
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    s390_vec_write_element64(v1, 0, MIN(first_equal, first_zero));
+    s390_vec_write_element64(v1, 1, 0);
+    if (first_zero == 16 && first_equal == 16) {
+        return 3; /* no match */
+    } else if (first_zero == 16) {
+        return 1; /* matching elements, no match for zero */
+    } else if (first_equal < first_zero) {
+        return 2; /* matching elements before match for zero */
+    }
+    return 0; /* match for zero */
+}
+
+#define DEF_VFEE_HELPER(BITS)                                                  \
+void HELPER(gvec_vfee##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vfee(v1, v2, v3, zs, MO_##BITS);                                           \
+}
+DEF_VFEE_HELPER(8)
+DEF_VFEE_HELPER(16)
+DEF_VFEE_HELPER(32)
+
+#define DEF_VFEE_CC_HELPER(BITS)                                               \
+void HELPER(gvec_vfee_cc##BITS)(void *v1, const void *v2, const void *v3,      \
+                                CPUS390XState *env, uint32_t desc)             \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vfee(v1, v2, v3, zs, MO_##BITS);                              \
+}
+DEF_VFEE_CC_HELPER(8)
+DEF_VFEE_CC_HELPER(16)
+DEF_VFEE_CC_HELPER(32)
+
+static int vfene(void *v1, const void *v2, const void *v3, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    uint64_t a0, a1, b0, b1, e0, e1, z0, z1;
+    uint64_t first_zero = 16;
+    uint64_t first_inequal;
+    bool smaller = false;
+
+    a0 = s390_vec_read_element64(v2, 0);
+    a1 = s390_vec_read_element64(v2, 1);
+    b0 = s390_vec_read_element64(v3, 0);
+    b1 = s390_vec_read_element64(v3, 1);
+    e0 = nonzero_search(a0 ^ b0, mask);
+    e1 = nonzero_search(a1 ^ b1, mask);
+    first_inequal = match_index(e0, e1);
+
+    /* identify the smaller element */
+    if (first_inequal < 16) {
+        uint8_t enr = first_inequal / (1 << es);
+        uint32_t a = s390_vec_read_element(v2, enr, es);
+        uint32_t b = s390_vec_read_element(v3, enr, es);
+
+        smaller = a < b;
+    }
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    s390_vec_write_element64(v1, 0, MIN(first_inequal, first_zero));
+    s390_vec_write_element64(v1, 1, 0);
+    if (first_zero == 16 && first_inequal == 16) {
+        return 3;
+    } else if (first_zero < first_inequal) {
+        return 0;
+    }
+    return smaller ? 1 : 2;
+}
+
+#define DEF_VFENE_HELPER(BITS)                                                 \
+void HELPER(gvec_vfene##BITS)(void *v1, const void *v2, const void *v3,        \
+                              uint32_t desc)                                   \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vfene(v1, v2, v3, zs, MO_##BITS);                                          \
+}
+DEF_VFENE_HELPER(8)
+DEF_VFENE_HELPER(16)
+DEF_VFENE_HELPER(32)
+
+#define DEF_VFENE_CC_HELPER(BITS)                                              \
+void HELPER(gvec_vfene_cc##BITS)(void *v1, const void *v2, const void *v3,     \
+                                 CPUS390XState *env, uint32_t desc)            \
+{                                                                              \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vfene(v1, v2, v3, zs, MO_##BITS);                             \
+}
+DEF_VFENE_CC_HELPER(8)
+DEF_VFENE_CC_HELPER(16)
+DEF_VFENE_CC_HELPER(32)
+
+static int vistr(void *v1, const void *v2, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    uint64_t a0 = s390_vec_read_element64(v2, 0);
+    uint64_t a1 = s390_vec_read_element64(v2, 1);
+    uint64_t z;
+    int cc = 3;
+
+    z = zero_search(a0, mask);
+    if (z) {
+        a0 &= ~(-1ull >> clz64(z));
+        a1 = 0;
+        cc = 0;
+    } else {
+        z = zero_search(a1, mask);
+        if (z) {
+            a1 &= ~(-1ull >> clz64(z));
+            cc = 0;
+        }
+    }
+
+    s390_vec_write_element64(v1, 0, a0);
+    s390_vec_write_element64(v1, 1, a1);
+    return cc;
+}
+
+#define DEF_VISTR_HELPER(BITS)                                                 \
+void HELPER(gvec_vistr##BITS)(void *v1, const void *v2, uint32_t desc)         \
+{                                                                              \
+    vistr(v1, v2, MO_##BITS);                                                  \
+}
+DEF_VISTR_HELPER(8)
+DEF_VISTR_HELPER(16)
+DEF_VISTR_HELPER(32)
+
+#define DEF_VISTR_CC_HELPER(BITS)                                              \
+void HELPER(gvec_vistr_cc##BITS)(void *v1, const void *v2, CPUS390XState *env, \
+                                uint32_t desc)                                 \
+{                                                                              \
+    env->cc_op = vistr(v1, v2, MO_##BITS);                                     \
+}
+DEF_VISTR_CC_HELPER(8)
+DEF_VISTR_CC_HELPER(16)
+DEF_VISTR_CC_HELPER(32)
+
+static bool element_compare(uint32_t data, uint32_t l, uint8_t c)
+{
+    const bool equal = extract32(c, 7, 1);
+    const bool lower = extract32(c, 6, 1);
+    const bool higher = extract32(c, 5, 1);
+
+    if (data < l) {
+        return lower;
+    } else if (data > l) {
+        return higher;
+    }
+    return equal;
+}
+
+static int vstrc(void *v1, const void *v2, const void *v3, const void *v4,
+                 bool in, bool rt, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    uint64_t a0 = s390_vec_read_element64(v2, 0);
+    uint64_t a1 = s390_vec_read_element64(v2, 1);
+    int first_zero = 16, first_match = 16;
+    S390Vector rt_result = {};
+    uint64_t z0, z1;
+    int i, j;
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    for (i = 0; i < 16 / (1 << es); i++) {
+        const uint32_t data = s390_vec_read_element(v2, i, es);
+        const int cur_byte = i * (1 << es);
+        bool any_match = false;
+
+        /* if we don't need a bit vector, we can stop early */
+        if (cur_byte == first_zero && !rt) {
+            break;
+        }
+
+        for (j = 0; j < 16 / (1 << es); j += 2) {
+            const uint32_t l1 = s390_vec_read_element(v3, j, es);
+            const uint32_t l2 = s390_vec_read_element(v3, j + 1, es);
+            /* we are only interested in the highest byte of each element */
+            const uint8_t c1 = s390_vec_read_element8(v4, j * (1 << es));
+            const uint8_t c2 = s390_vec_read_element8(v4, (j + 1) * (1 << es));
+
+            if (element_compare(data, l1, c1) &&
+                element_compare(data, l2, c2)) {
+                any_match = true;
+                break;
+            }
+        }
+        /* invert the result if requested */
+        any_match = in ^ any_match;
+
+        if (any_match) {
+            /* indicate bit vector if requested */
+            if (rt) {
+                const uint64_t val = -1ull;
+
+                first_match = MIN(cur_byte, first_match);
+                s390_vec_write_element(&rt_result, i, es, val);
+            } else {
+                /* stop on the first match */
+                first_match = cur_byte;
+                break;
+            }
+        }
+    }
+
+    if (rt) {
+        *(S390Vector *)v1 = rt_result;
+    } else {
+        s390_vec_write_element64(v1, 0, MIN(first_match, first_zero));
+        s390_vec_write_element64(v1, 1, 0);
+    }
+
+    if (first_zero == 16 && first_match == 16) {
+        return 3; /* no match */
+    } else if (first_zero == 16) {
+        return 1; /* matching elements, no match for zero */
+    } else if (first_match < first_zero) {
+        return 2; /* matching elements before match for zero */
+    }
+    return 0; /* match for zero */
+}
+
+#define DEF_VSTRC_HELPER(BITS)                                                 \
+void HELPER(gvec_vstrc##BITS)(void *v1, const void *v2, const void *v3,        \
+                              const void *v4, uint32_t desc)                   \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vstrc(v1, v2, v3, v4, in, 0, zs, MO_##BITS);                               \
+}
+DEF_VSTRC_HELPER(8)
+DEF_VSTRC_HELPER(16)
+DEF_VSTRC_HELPER(32)
+
+#define DEF_VSTRC_RT_HELPER(BITS)                                              \
+void HELPER(gvec_vstrc_rt##BITS)(void *v1, const void *v2, const void *v3,     \
+                                 const void *v4, uint32_t desc)                \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vstrc(v1, v2, v3, v4, in, 1, zs, MO_##BITS);                               \
+}
+DEF_VSTRC_RT_HELPER(8)
+DEF_VSTRC_RT_HELPER(16)
+DEF_VSTRC_RT_HELPER(32)
+
+#define DEF_VSTRC_CC_HELPER(BITS)                                              \
+void HELPER(gvec_vstrc_cc##BITS)(void *v1, const void *v2, const void *v3,     \
+                                 const void *v4, CPUS390XState *env,           \
+                                 uint32_t desc)                                \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vstrc(v1, v2, v3, v4, in, 0, zs, MO_##BITS);                  \
+}
+DEF_VSTRC_CC_HELPER(8)
+DEF_VSTRC_CC_HELPER(16)
+DEF_VSTRC_CC_HELPER(32)
+
+#define DEF_VSTRC_CC_RT_HELPER(BITS)                                           \
+void HELPER(gvec_vstrc_cc_rt##BITS)(void *v1, const void *v2, const void *v3,  \
+                                    const void *v4, CPUS390XState *env,        \
+                                    uint32_t desc)                             \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vstrc(v1, v2, v3, v4, in, 1, zs, MO_##BITS);                  \
+}
+DEF_VSTRC_CC_RT_HELPER(8)
+DEF_VSTRC_CC_RT_HELPER(16)
+DEF_VSTRC_CC_RT_HELPER(32)