diff --git a/linux-user/ppc/signal.c b/linux-user/ppc/signal.c
index ecd99736b7..20a02c197c 100644
--- a/linux-user/ppc/signal.c
+++ b/linux-user/ppc/signal.c
@@ -35,12 +35,26 @@ struct target_mcontext {
     target_ulong mc_gregs[48];
     /* Includes fpscr.  */
     uint64_t mc_fregs[33];
+
 #if defined(TARGET_PPC64)
     /* Pointer to the vector regs */
     target_ulong v_regs;
+    /*
+     * On ppc64, this mcontext structure is naturally *unaligned*,
+     * or rather it is aligned on a 8 bytes boundary but not on
+     * a 16 byte boundary.  This pad fixes it up.  This is why we
+     * cannot use ppc_avr_t, which would force alignment.  This is
+     * also why the vector regs are referenced in the ABI by the
+     * v_regs pointer above so any amount of padding can be added here.
+     */
+    target_ulong pad;
+    /* VSCR and VRSAVE are saved separately.  Also reserve space for VSX. */
+    struct {
+        uint64_t altivec[34 + 16][2];
+    } mc_vregs;
 #else
     target_ulong mc_pad[2];
-#endif
+
     /* We need to handle Altivec and SPE at the same time, which no
        kernel needs to do.  Fortunately, the kernel defines this bit to
        be Altivec-register-large all the time, rather than trying to
@@ -48,32 +62,14 @@ struct target_mcontext {
     union {
         /* SPE vector registers.  One extra for SPEFSCR.  */
         uint32_t spe[33];
-        /* Altivec vector registers.  The packing of VSCR and VRSAVE
-           varies depending on whether we're PPC64 or not: PPC64 splits
-           them apart; PPC32 stuffs them together.
-           We also need to account for the VSX registers on PPC64
-        */
-#if defined(TARGET_PPC64)
-#define QEMU_NVRREG (34 + 16)
-        /* On ppc64, this mcontext structure is naturally *unaligned*,
-         * or rather it is aligned on a 8 bytes boundary but not on
-         * a 16 bytes one. This pad fixes it up. This is also why the
-         * vector regs are referenced by the v_regs pointer above so
-         * any amount of padding can be added here
+        /*
+         * Altivec vector registers.  One extra for VRSAVE.
+         * On ppc32, we are already aligned to 16 bytes.  We could
+         * use ppc_avr_t, but choose to share the same type as ppc64.
          */
-        target_ulong pad;
-#else
-        /* On ppc32, we are already aligned to 16 bytes */
-#define QEMU_NVRREG 33
-#endif
-        /* We cannot use ppc_avr_t here as we do *not* want the implied
-         * 16-bytes alignment that would result from it. This would have
-         * the effect of making the whole struct target_mcontext aligned
-         * which breaks the layout of struct target_ucontext on ppc64.
-         */
-        uint64_t altivec[QEMU_NVRREG][2];
-#undef QEMU_NVRREG
+        uint64_t altivec[33][2];
     } mc_vregs;
+#endif
 };
 
 /* See arch/powerpc/include/asm/sigcontext.h.  */
@@ -278,6 +274,7 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
         __put_user((uint32_t)env->spr[SPR_VRSAVE], vrsave);
     }
 
+#if defined(TARGET_PPC64)
     /* Save VSX second halves */
     if (env->insns_flags2 & PPC2_VSX) {
         uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
@@ -286,6 +283,7 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
             __put_user(*vsrl, &vsregs[i]);
         }
     }
+#endif
 
     /* Save floating point registers.  */
     if (env->insns_flags & PPC_FLOAT) {
@@ -296,22 +294,18 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
         __put_user((uint64_t) env->fpscr, &frame->mc_fregs[32]);
     }
 
+#if !defined(TARGET_PPC64)
     /* Save SPE registers.  The kernel only saves the high half.  */
     if (env->insns_flags & PPC_SPE) {
-#if defined(TARGET_PPC64)
-        for (i = 0; i < ARRAY_SIZE(env->gpr); i++) {
-            __put_user(env->gpr[i] >> 32, &frame->mc_vregs.spe[i]);
-        }
-#else
         for (i = 0; i < ARRAY_SIZE(env->gprh); i++) {
             __put_user(env->gprh[i], &frame->mc_vregs.spe[i]);
         }
-#endif
         /* Set MSR_SPE in the saved MSR value to indicate that
            frame->mc_vregs contains valid data.  */
         msr |= MSR_SPE;
         __put_user(env->spe_fscr, &frame->mc_vregs.spe[32]);
     }
+#endif
 
     /* Store MSR.  */
     __put_user(msr, &frame->mc_gregs[TARGET_PT_MSR]);
@@ -392,6 +386,7 @@ static void restore_user_regs(CPUPPCState *env,
         __get_user(env->spr[SPR_VRSAVE], vrsave);
     }
 
+#if defined(TARGET_PPC64)
     /* Restore VSX second halves */
     if (env->insns_flags2 & PPC2_VSX) {
         uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
@@ -400,6 +395,7 @@ static void restore_user_regs(CPUPPCState *env,
             __get_user(*vsrl, &vsregs[i]);
         }
     }
+#endif
 
     /* Restore floating point registers.  */
     if (env->insns_flags & PPC_FLOAT) {
@@ -412,22 +408,15 @@ static void restore_user_regs(CPUPPCState *env,
         env->fpscr = (uint32_t) fpscr;
     }
 
+#if !defined(TARGET_PPC64)
     /* Save SPE registers.  The kernel only saves the high half.  */
     if (env->insns_flags & PPC_SPE) {
-#if defined(TARGET_PPC64)
-        for (i = 0; i < ARRAY_SIZE(env->gpr); i++) {
-            uint32_t hi;
-
-            __get_user(hi, &frame->mc_vregs.spe[i]);
-            env->gpr[i] = ((uint64_t)hi << 32) | ((uint32_t) env->gpr[i]);
-        }
-#else
         for (i = 0; i < ARRAY_SIZE(env->gprh); i++) {
             __get_user(env->gprh[i], &frame->mc_vregs.spe[i]);
         }
-#endif
         __get_user(env->spe_fscr, &frame->mc_vregs.spe[32]);
     }
+#endif
 }
 
 #if !defined(TARGET_PPC64)
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 03d0667e8f..2692f76130 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -2816,11 +2816,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)
 #if defined(TARGET_PPC64)
 int kvm_handle_nmi(PowerPCCPU *cpu, struct kvm_run *run)
 {
-    bool recovered = run->flags & KVM_RUN_PPC_NMI_DISP_FULLY_RECOV;
+    uint16_t flags = run->flags & KVM_RUN_PPC_NMI_DISP_MASK;
 
     cpu_synchronize_state(CPU(cpu));
 
-    spapr_mce_req_event(cpu, recovered);
+    spapr_mce_req_event(cpu, flags == KVM_RUN_PPC_NMI_DISP_FULLY_RECOV);
 
     return 0;
 }
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index b207fb5386..9959259dba 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -4361,30 +4361,34 @@ static void gen_mtmsrd(DisasContext *ctx)
     CHK_SV;
 
 #if !defined(CONFIG_USER_ONLY)
+    if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) {
+        gen_io_start();
+    }
     if (ctx->opcode & 0x00010000) {
-        /* Special form that does not need any synchronisation */
+        /* L=1 form only updates EE and RI */
         TCGv t0 = tcg_temp_new();
+        TCGv t1 = tcg_temp_new();
         tcg_gen_andi_tl(t0, cpu_gpr[rS(ctx->opcode)],
                         (1 << MSR_RI) | (1 << MSR_EE));
-        tcg_gen_andi_tl(cpu_msr, cpu_msr,
+        tcg_gen_andi_tl(t1, cpu_msr,
                         ~(target_ulong)((1 << MSR_RI) | (1 << MSR_EE)));
-        tcg_gen_or_tl(cpu_msr, cpu_msr, t0);
+        tcg_gen_or_tl(t1, t1, t0);
+
+        gen_helper_store_msr(cpu_env, t1);
         tcg_temp_free(t0);
+        tcg_temp_free(t1);
+
     } else {
         /*
          * XXX: we need to update nip before the store if we enter
          *      power saving mode, we will exit the loop directly from
          *      ppc_store_msr
          */
-        if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) {
-            gen_io_start();
-        }
         gen_update_nip(ctx, ctx->base.pc_next);
         gen_helper_store_msr(cpu_env, cpu_gpr[rS(ctx->opcode)]);
-        /* Must stop the translation as machine state (may have) changed */
-        /* Note that mtmsr is not always defined as context-synchronizing */
-        gen_stop_exception(ctx);
     }
+    /* Must stop the translation as machine state (may have) changed */
+    gen_stop_exception(ctx);
 #endif /* !defined(CONFIG_USER_ONLY) */
 }
 #endif /* defined(TARGET_PPC64) */
@@ -4394,15 +4398,23 @@ static void gen_mtmsr(DisasContext *ctx)
     CHK_SV;
 
 #if !defined(CONFIG_USER_ONLY)
-   if (ctx->opcode & 0x00010000) {
-        /* Special form that does not need any synchronisation */
+    if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) {
+        gen_io_start();
+    }
+    if (ctx->opcode & 0x00010000) {
+        /* L=1 form only updates EE and RI */
         TCGv t0 = tcg_temp_new();
+        TCGv t1 = tcg_temp_new();
         tcg_gen_andi_tl(t0, cpu_gpr[rS(ctx->opcode)],
                         (1 << MSR_RI) | (1 << MSR_EE));
-        tcg_gen_andi_tl(cpu_msr, cpu_msr,
+        tcg_gen_andi_tl(t1, cpu_msr,
                         ~(target_ulong)((1 << MSR_RI) | (1 << MSR_EE)));
-        tcg_gen_or_tl(cpu_msr, cpu_msr, t0);
+        tcg_gen_or_tl(t1, t1, t0);
+
+        gen_helper_store_msr(cpu_env, t1);
         tcg_temp_free(t0);
+        tcg_temp_free(t1);
+
     } else {
         TCGv msr = tcg_temp_new();
 
@@ -4411,9 +4423,6 @@ static void gen_mtmsr(DisasContext *ctx)
          *      power saving mode, we will exit the loop directly from
          *      ppc_store_msr
          */
-        if (tb_cflags(ctx->base.tb) & CF_USE_ICOUNT) {
-            gen_io_start();
-        }
         gen_update_nip(ctx, ctx->base.pc_next);
 #if defined(TARGET_PPC64)
         tcg_gen_deposit_tl(msr, cpu_msr, cpu_gpr[rS(ctx->opcode)], 0, 32);
@@ -4422,10 +4431,9 @@ static void gen_mtmsr(DisasContext *ctx)
 #endif
         gen_helper_store_msr(cpu_env, msr);
         tcg_temp_free(msr);
-        /* Must stop the translation as machine state (may have) changed */
-        /* Note that mtmsr is not always defined as context-synchronizing */
-        gen_stop_exception(ctx);
     }
+    /* Must stop the translation as machine state (may have) changed */
+    gen_stop_exception(ctx);
 #endif
 }