diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c
index 9e5b2fb31c..0c43e0eef8 100644
--- a/target/arm/arch_dump.c
+++ b/target/arm/arch_dump.c
@@ -100,7 +100,7 @@ static int aarch64_write_elf64_prfpreg(WriteCoreDumpFunction f,
     aarch64_note_init(&note, s, "CORE", 5, NT_PRFPREG, sizeof(note.vfp));
 
     for (i = 0; i < 64; ++i) {
-        note.vfp.vregs[i] = cpu_to_dump64(s, float64_val(env->vfp.regs[i]));
+        note.vfp.vregs[i] = cpu_to_dump64(s, env->vfp.regs[i]);
     }
 
     if (s->dump_info.d_endian == ELFDATA2MSB) {
@@ -229,7 +229,7 @@ static int arm_write_elf32_vfp(WriteCoreDumpFunction f, CPUARMState *env,
     arm_note_init(&note, s, "LINUX", 6, NT_ARM_VFP, sizeof(note.vfp));
 
     for (i = 0; i < 32; ++i) {
-        note.vfp.vregs[i] = cpu_to_dump64(s, float64_val(env->vfp.regs[i]));
+        note.vfp.vregs[i] = cpu_to_dump64(s, env->vfp.regs[i]);
     }
 
     note.vfp.fpscr = cpu_to_dump32(s, vfp_get_fpscr(env));
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 96316700dd..76ab7953a6 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -492,7 +492,7 @@ typedef struct CPUARMState {
          * the two execution states, and means we do not need to explicitly
          * map these registers when changing states.
          */
-        float64 regs[64];
+        uint64_t regs[64];
 
         uint32_t xregs[16];
         /* We store these fpcsr fields separately for convenience.  */
diff --git a/target/arm/helper.c b/target/arm/helper.c
index bd05f8acb8..ff5d78c4b8 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -64,15 +64,15 @@ static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg)
     /* VFP data registers are always little-endian.  */
     nregs = arm_feature(env, ARM_FEATURE_VFP3) ? 32 : 16;
     if (reg < nregs) {
-        stfq_le_p(buf, env->vfp.regs[reg]);
+        stq_le_p(buf, env->vfp.regs[reg]);
         return 8;
     }
     if (arm_feature(env, ARM_FEATURE_NEON)) {
         /* Aliases for Q regs.  */
         nregs += 16;
         if (reg < nregs) {
-            stfq_le_p(buf, env->vfp.regs[(reg - 32) * 2]);
-            stfq_le_p(buf + 8, env->vfp.regs[(reg - 32) * 2 + 1]);
+            stq_le_p(buf, env->vfp.regs[(reg - 32) * 2]);
+            stq_le_p(buf + 8, env->vfp.regs[(reg - 32) * 2 + 1]);
             return 16;
         }
     }
@@ -90,14 +90,14 @@ static int vfp_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg)
 
     nregs = arm_feature(env, ARM_FEATURE_VFP3) ? 32 : 16;
     if (reg < nregs) {
-        env->vfp.regs[reg] = ldfq_le_p(buf);
+        env->vfp.regs[reg] = ldq_le_p(buf);
         return 8;
     }
     if (arm_feature(env, ARM_FEATURE_NEON)) {
         nregs += 16;
         if (reg < nregs) {
-            env->vfp.regs[(reg - 32) * 2] = ldfq_le_p(buf);
-            env->vfp.regs[(reg - 32) * 2 + 1] = ldfq_le_p(buf + 8);
+            env->vfp.regs[(reg - 32) * 2] = ldq_le_p(buf);
+            env->vfp.regs[(reg - 32) * 2 + 1] = ldq_le_p(buf + 8);
             return 16;
         }
     }
@@ -114,8 +114,8 @@ static int aarch64_fpu_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg)
     switch (reg) {
     case 0 ... 31:
         /* 128 bit FP register */
-        stfq_le_p(buf, env->vfp.regs[reg * 2]);
-        stfq_le_p(buf + 8, env->vfp.regs[reg * 2 + 1]);
+        stq_le_p(buf, env->vfp.regs[reg * 2]);
+        stq_le_p(buf + 8, env->vfp.regs[reg * 2 + 1]);
         return 16;
     case 32:
         /* FPSR */
@@ -135,8 +135,8 @@ static int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg)
     switch (reg) {
     case 0 ... 31:
         /* 128 bit FP register */
-        env->vfp.regs[reg * 2] = ldfq_le_p(buf);
-        env->vfp.regs[reg * 2 + 1] = ldfq_le_p(buf + 8);
+        env->vfp.regs[reg * 2] = ldq_le_p(buf);
+        env->vfp.regs[reg * 2 + 1] = ldq_le_p(buf + 8);
         return 16;
     case 32:
         /* FPSR */
diff --git a/target/arm/machine.c b/target/arm/machine.c
index 176274629c..a85c2430d3 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -50,7 +50,7 @@ static const VMStateDescription vmstate_vfp = {
     .minimum_version_id = 3,
     .needed = vfp_needed,
     .fields = (VMStateField[]) {
-        VMSTATE_FLOAT64_ARRAY(env.vfp.regs, ARMCPU, 64),
+        VMSTATE_UINT64_ARRAY(env.vfp.regs, ARMCPU, 64),
         /* The xregs array is a little awkward because element 1 (FPSCR)
          * requires a specific accessor, so we have to split it up in
          * the vmstate:
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 6d9b3af64c..c14fb4185c 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -165,12 +165,12 @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
     if (flags & CPU_DUMP_FPU) {
         int numvfpregs = 32;
         for (i = 0; i < numvfpregs; i += 2) {
-            uint64_t vlo = float64_val(env->vfp.regs[i * 2]);
-            uint64_t vhi = float64_val(env->vfp.regs[(i * 2) + 1]);
+            uint64_t vlo = env->vfp.regs[i * 2];
+            uint64_t vhi = env->vfp.regs[(i * 2) + 1];
             cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 " ",
                         i, vhi, vlo);
-            vlo = float64_val(env->vfp.regs[(i + 1) * 2]);
-            vhi = float64_val(env->vfp.regs[((i + 1) * 2) + 1]);
+            vlo = env->vfp.regs[(i + 1) * 2];
+            vhi = env->vfp.regs[((i + 1) * 2) + 1];
             cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 "\n",
                         i + 1, vhi, vlo);
         }
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 852d2a75b1..cfe49bf579 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -12572,7 +12572,7 @@ void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf,
             numvfpregs += 16;
         }
         for (i = 0; i < numvfpregs; i++) {
-            uint64_t v = float64_val(env->vfp.regs[i]);
+            uint64_t v = env->vfp.regs[i];
             cpu_fprintf(f, "s%02d=%08x s%02d=%08x d%02d=%016" PRIx64 "\n",
                         i * 2, (uint32_t)v,
                         i * 2 + 1, (uint32_t)(v >> 32),