summary refs log tree commit diff stats
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/i386/Makefile.objs2
-rw-r--r--target/i386/cpu.c9
-rw-r--r--target/i386/cpu.h3
-rw-r--r--target/ppc/cpu-qom.h1
-rw-r--r--target/ppc/cpu.h59
-rw-r--r--target/ppc/excp_helper.c30
-rw-r--r--target/ppc/internal.h27
-rw-r--r--target/ppc/kvm.c206
-rw-r--r--target/ppc/kvm_ppc.h23
-rw-r--r--target/ppc/machine.c8
-rw-r--r--target/ppc/mmu-hash64.c2
-rw-r--r--target/ppc/translate.c22
-rw-r--r--target/ppc/translate/vmx-impl.inc.c27
-rw-r--r--target/ppc/translate/vsx-impl.inc.c65
-rw-r--r--target/ppc/translate_init.inc.c7
15 files changed, 299 insertions, 192 deletions
diff --git a/target/i386/Makefile.objs b/target/i386/Makefile.objs
index cb9c265525..48e0c28434 100644
--- a/target/i386/Makefile.objs
+++ b/target/i386/Makefile.objs
@@ -3,10 +3,10 @@ obj-$(CONFIG_TCG) += translate.o
 obj-$(CONFIG_TCG) += bpt_helper.o cc_helper.o excp_helper.o fpu_helper.o
 obj-$(CONFIG_TCG) += int_helper.o mem_helper.o misc_helper.o mpx_helper.o
 obj-$(CONFIG_TCG) += seg_helper.o smm_helper.o svm_helper.o
+obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
 ifeq ($(CONFIG_SOFTMMU),y)
 obj-y += machine.o arch_memory_mapping.o arch_dump.o monitor.o
 obj-$(CONFIG_KVM) += kvm.o
-obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
 obj-$(CONFIG_HYPERV) += hyperv.o
 obj-$(call lnot,$(CONFIG_HYPERV)) += hyperv-stub.o
 ifeq ($(CONFIG_WIN32),y)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index d3aa6a815b..d90c01a059 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5031,6 +5031,13 @@ static void x86_cpu_expand_features(X86CPU *cpu, Error **errp)
         x86_cpu_adjust_feat_level(cpu, FEAT_C000_0001_EDX);
         x86_cpu_adjust_feat_level(cpu, FEAT_SVM);
         x86_cpu_adjust_feat_level(cpu, FEAT_XSAVE);
+
+        /* Intel Processor Trace requires CPUID[0x14] */
+        if ((env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) &&
+             kvm_enabled() && cpu->intel_pt_auto_level) {
+            x86_cpu_adjust_level(cpu, &cpu->env.cpuid_min_level, 0x14);
+        }
+
         /* SVM requires CPUID[0x8000000A] */
         if (env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_SVM) {
             x86_cpu_adjust_level(cpu, &env->cpuid_min_xlevel, 0x8000000A);
@@ -5824,6 +5831,8 @@ static Property x86_cpu_properties[] = {
     DEFINE_PROP_INT32("x-hv-max-vps", X86CPU, hv_max_vps, -1),
     DEFINE_PROP_BOOL("x-hv-synic-kvm-only", X86CPU, hyperv_synic_kvm_only,
                      false),
+    DEFINE_PROP_BOOL("x-intel-pt-auto-level", X86CPU, intel_pt_auto_level,
+                     true),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 95112b9118..83fb522554 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1454,6 +1454,9 @@ struct X86CPU {
     /* Enable auto level-increase for all CPUID leaves */
     bool full_cpuid_auto_level;
 
+    /* Enable auto level-increase for Intel Processor Trace leave */
+    bool intel_pt_auto_level;
+
     /* if true fill the top bits of the MTRR_PHYSMASKn variable range */
     bool fill_mtrr_mask;
 
diff --git a/target/ppc/cpu-qom.h b/target/ppc/cpu-qom.h
index ae51fe754e..be9b4c30c3 100644
--- a/target/ppc/cpu-qom.h
+++ b/target/ppc/cpu-qom.h
@@ -190,6 +190,7 @@ typedef struct PowerPCCPUClass {
 #endif
     const PPCHash64Options *hash64_opts;
     struct ppc_radix_page_info *radix_page_info;
+    uint32_t lrg_decr_bits;
     void (*init_proc)(CPUPPCState *env);
     int  (*check_pow)(CPUPPCState *env);
     int (*handle_mmu_fault)(PowerPCCPU *cpu, vaddr eaddr, int rwx, int mmu_idx);
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 26604ddf98..fc12b4688e 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1321,10 +1321,10 @@ uint32_t cpu_ppc_load_atbu (CPUPPCState *env);
 void cpu_ppc_store_atbl (CPUPPCState *env, uint32_t value);
 void cpu_ppc_store_atbu (CPUPPCState *env, uint32_t value);
 bool ppc_decr_clear_on_delivery(CPUPPCState *env);
-uint32_t cpu_ppc_load_decr (CPUPPCState *env);
-void cpu_ppc_store_decr (CPUPPCState *env, uint32_t value);
-uint32_t cpu_ppc_load_hdecr (CPUPPCState *env);
-void cpu_ppc_store_hdecr (CPUPPCState *env, uint32_t value);
+target_ulong cpu_ppc_load_decr(CPUPPCState *env);
+void cpu_ppc_store_decr(CPUPPCState *env, target_ulong value);
+target_ulong cpu_ppc_load_hdecr(CPUPPCState *env);
+void cpu_ppc_store_hdecr(CPUPPCState *env, target_ulong value);
 uint64_t cpu_ppc_load_purr (CPUPPCState *env);
 uint32_t cpu_ppc601_load_rtcl (CPUPPCState *env);
 uint32_t cpu_ppc601_load_rtcu (CPUPPCState *env);
@@ -2563,19 +2563,64 @@ static inline bool lsw_reg_in_range(int start, int nregs, int rx)
 }
 
 /* Accessors for FP, VMX and VSX registers */
+#if defined(HOST_WORDS_BIGENDIAN)
+#define VsrB(i) u8[i]
+#define VsrSB(i) s8[i]
+#define VsrH(i) u16[i]
+#define VsrSH(i) s16[i]
+#define VsrW(i) u32[i]
+#define VsrSW(i) s32[i]
+#define VsrD(i) u64[i]
+#define VsrSD(i) s64[i]
+#else
+#define VsrB(i) u8[15 - (i)]
+#define VsrSB(i) s8[15 - (i)]
+#define VsrH(i) u16[7 - (i)]
+#define VsrSH(i) s16[7 - (i)]
+#define VsrW(i) u32[3 - (i)]
+#define VsrSW(i) s32[3 - (i)]
+#define VsrD(i) u64[1 - (i)]
+#define VsrSD(i) s64[1 - (i)]
+#endif
+
+static inline int vsr64_offset(int i, bool high)
+{
+    return offsetof(CPUPPCState, vsr[i].VsrD(high ? 0 : 1));
+}
+
+static inline int vsr_full_offset(int i)
+{
+    return offsetof(CPUPPCState, vsr[i].u64[0]);
+}
+
+static inline int fpr_offset(int i)
+{
+    return vsr64_offset(i, true);
+}
+
 static inline uint64_t *cpu_fpr_ptr(CPUPPCState *env, int i)
 {
-    return &env->vsr[i].u64[0];
+    return (uint64_t *)((uintptr_t)env + fpr_offset(i));
 }
 
 static inline uint64_t *cpu_vsrl_ptr(CPUPPCState *env, int i)
 {
-    return &env->vsr[i].u64[1];
+    return (uint64_t *)((uintptr_t)env + vsr64_offset(i, false));
+}
+
+static inline long avr64_offset(int i, bool high)
+{
+    return vsr64_offset(i + 32, high);
+}
+
+static inline int avr_full_offset(int i)
+{
+    return vsr_full_offset(i + 32);
 }
 
 static inline ppc_avr_t *cpu_avr_ptr(CPUPPCState *env, int i)
 {
-    return &env->vsr[32 + i];
+    return (ppc_avr_t *)((uintptr_t)env + avr_full_offset(i));
 }
 
 void dump_mmu(FILE *f, fprintf_function cpu_fprintf, CPUPPCState *env);
diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c
index 39bedbb11d..beafcf1ebd 100644
--- a/target/ppc/excp_helper.c
+++ b/target/ppc/excp_helper.c
@@ -107,6 +107,24 @@ static int powerpc_reset_wakeup(CPUState *cs, CPUPPCState *env, int excp,
     return POWERPC_EXCP_RESET;
 }
 
+static uint64_t ppc_excp_vector_offset(CPUState *cs, int ail)
+{
+    uint64_t offset = 0;
+
+    switch (ail) {
+    case AIL_0001_8000:
+        offset = 0x18000;
+        break;
+    case AIL_C000_0000_0000_4000:
+        offset = 0xc000000000004000ull;
+        break;
+    default:
+        cpu_abort(cs, "Invalid AIL combination %d\n", ail);
+        break;
+    }
+
+    return offset;
+}
 
 /* Note that this function should be greatly optimized
  * when called with a constant excp, from ppc_hw_interrupt
@@ -708,17 +726,7 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp)
     /* Handle AIL */
     if (ail) {
         new_msr |= (1 << MSR_IR) | (1 << MSR_DR);
-        switch(ail) {
-        case AIL_0001_8000:
-            vector |= 0x18000;
-            break;
-        case AIL_C000_0000_0000_4000:
-            vector |= 0xc000000000004000ull;
-            break;
-        default:
-            cpu_abort(cs, "Invalid AIL combination %d\n", ail);
-            break;
-        }
+        vector |= ppc_excp_vector_offset(cs, ail);
     }
 
 #if defined(TARGET_PPC64)
diff --git a/target/ppc/internal.h b/target/ppc/internal.h
index f26a71ffcf..fb6f64ed1e 100644
--- a/target/ppc/internal.h
+++ b/target/ppc/internal.h
@@ -204,35 +204,16 @@ EXTRACT_HELPER(IMM8, 11, 8);
 EXTRACT_HELPER(DCMX, 16, 7);
 EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1, 6, 6);
 
-#if defined(HOST_WORDS_BIGENDIAN)
-#define VsrB(i) u8[i]
-#define VsrSB(i) s8[i]
-#define VsrH(i) u16[i]
-#define VsrSH(i) s16[i]
-#define VsrW(i) u32[i]
-#define VsrSW(i) s32[i]
-#define VsrD(i) u64[i]
-#define VsrSD(i) s64[i]
-#else
-#define VsrB(i) u8[15 - (i)]
-#define VsrSB(i) s8[15 - (i)]
-#define VsrH(i) u16[7 - (i)]
-#define VsrSH(i) s16[7 - (i)]
-#define VsrW(i) u32[3 - (i)]
-#define VsrSW(i) s32[3 - (i)]
-#define VsrD(i) u64[1 - (i)]
-#define VsrSD(i) s64[1 - (i)]
-#endif
 static inline void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
 {
-    vsr->VsrD(0) = env->vsr[n].u64[0];
-    vsr->VsrD(1) = env->vsr[n].u64[1];
+    vsr->VsrD(0) = env->vsr[n].VsrD(0);
+    vsr->VsrD(1) = env->vsr[n].VsrD(1);
 }
 
 static inline void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
 {
-    env->vsr[n].u64[0] = vsr->VsrD(0);
-    env->vsr[n].u64[1] = vsr->VsrD(1);
+    env->vsr[n].VsrD(0) = vsr->VsrD(0);
+    env->vsr[n].VsrD(1) = vsr->VsrD(1);
 }
 
 void helper_compute_fprf_float16(CPUPPCState *env, float16 arg);
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index d01852fe31..2427c8ee13 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -90,7 +90,9 @@ static int cap_ppc_pvr_compat;
 static int cap_ppc_safe_cache;
 static int cap_ppc_safe_bounds_check;
 static int cap_ppc_safe_indirect_branch;
+static int cap_ppc_count_cache_flush_assist;
 static int cap_ppc_nested_kvm_hv;
+static int cap_large_decr;
 
 static uint32_t debug_inst_opcode;
 
@@ -124,6 +126,7 @@ static bool kvmppc_is_pr(KVMState *ks)
 
 static int kvm_ppc_register_host_cpu_type(MachineState *ms);
 static void kvmppc_get_cpu_characteristics(KVMState *s);
+static int kvmppc_get_dec_bits(void);
 
 int kvm_arch_init(MachineState *ms, KVMState *s)
 {
@@ -151,6 +154,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
     cap_resize_hpt = kvm_vm_check_extension(s, KVM_CAP_SPAPR_RESIZE_HPT);
     kvmppc_get_cpu_characteristics(s);
     cap_ppc_nested_kvm_hv = kvm_vm_check_extension(s, KVM_CAP_PPC_NESTED_HV);
+    cap_large_decr = kvmppc_get_dec_bits();
     /*
      * Note: setting it to false because there is not such capability
      * in KVM at this moment.
@@ -752,7 +756,7 @@ static int kvm_get_fp(CPUState *cs)
 static int kvm_get_vpa(CPUState *cs)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
-    sPAPRCPUState *spapr_cpu = spapr_cpu_state(cpu);
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
     struct kvm_one_reg reg;
     int ret;
 
@@ -792,7 +796,7 @@ static int kvm_get_vpa(CPUState *cs)
 static int kvm_put_vpa(CPUState *cs)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
-    sPAPRCPUState *spapr_cpu = spapr_cpu_state(cpu);
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
     struct kvm_one_reg reg;
     int ret;
 
@@ -1593,70 +1597,93 @@ void kvm_arch_update_guest_debug(CPUState *cs, struct kvm_guest_debug *dbg)
     }
 }
 
-static int kvm_handle_debug(PowerPCCPU *cpu, struct kvm_run *run)
+static int kvm_handle_hw_breakpoint(CPUState *cs,
+                                    struct kvm_debug_exit_arch *arch_info)
 {
-    CPUState *cs = CPU(cpu);
-    CPUPPCState *env = &cpu->env;
-    struct kvm_debug_exit_arch *arch_info = &run->debug.arch;
     int handle = 0;
     int n;
     int flag = 0;
 
-    if (cs->singlestep_enabled) {
-        handle = 1;
-    } else if (arch_info->status) {
-        if (nb_hw_breakpoint + nb_hw_watchpoint > 0) {
-            if (arch_info->status & KVMPPC_DEBUG_BREAKPOINT) {
-                n = find_hw_breakpoint(arch_info->address, GDB_BREAKPOINT_HW);
-                if (n >= 0) {
-                    handle = 1;
-                }
-            } else if (arch_info->status & (KVMPPC_DEBUG_WATCH_READ |
-                                            KVMPPC_DEBUG_WATCH_WRITE)) {
-                n = find_hw_watchpoint(arch_info->address,  &flag);
-                if (n >= 0) {
-                    handle = 1;
-                    cs->watchpoint_hit = &hw_watchpoint;
-                    hw_watchpoint.vaddr = hw_debug_points[n].addr;
-                    hw_watchpoint.flags = flag;
-                }
+    if (nb_hw_breakpoint + nb_hw_watchpoint > 0) {
+        if (arch_info->status & KVMPPC_DEBUG_BREAKPOINT) {
+            n = find_hw_breakpoint(arch_info->address, GDB_BREAKPOINT_HW);
+            if (n >= 0) {
+                handle = 1;
+            }
+        } else if (arch_info->status & (KVMPPC_DEBUG_WATCH_READ |
+                                        KVMPPC_DEBUG_WATCH_WRITE)) {
+            n = find_hw_watchpoint(arch_info->address,  &flag);
+            if (n >= 0) {
+                handle = 1;
+                cs->watchpoint_hit = &hw_watchpoint;
+                hw_watchpoint.vaddr = hw_debug_points[n].addr;
+                hw_watchpoint.flags = flag;
             }
         }
-    } else if (kvm_find_sw_breakpoint(cs, arch_info->address)) {
-        handle = 1;
-    } else {
-        /* QEMU is not able to handle debug exception, so inject
-         * program exception to guest;
-         * Yes program exception NOT debug exception !!
-         * When QEMU is using debug resources then debug exception must
-         * be always set. To achieve this we set MSR_DE and also set
-         * MSRP_DEP so guest cannot change MSR_DE.
-         * When emulating debug resource for guest we want guest
-         * to control MSR_DE (enable/disable debug interrupt on need).
-         * Supporting both configurations are NOT possible.
-         * So the result is that we cannot share debug resources
-         * between QEMU and Guest on BOOKE architecture.
-         * In the current design QEMU gets the priority over guest,
-         * this means that if QEMU is using debug resources then guest
-         * cannot use them;
-         * For software breakpoint QEMU uses a privileged instruction;
-         * So there cannot be any reason that we are here for guest
-         * set debug exception, only possibility is guest executed a
-         * privileged / illegal instruction and that's why we are
-         * injecting a program interrupt.
-         */
+    }
+    return handle;
+}
 
-        cpu_synchronize_state(cs);
-        /* env->nip is PC, so increment this by 4 to use
-         * ppc_cpu_do_interrupt(), which set srr0 = env->nip - 4.
-         */
-        env->nip += 4;
-        cs->exception_index = POWERPC_EXCP_PROGRAM;
-        env->error_code = POWERPC_EXCP_INVAL;
-        ppc_cpu_do_interrupt(cs);
+static int kvm_handle_singlestep(void)
+{
+    return 1;
+}
+
+static int kvm_handle_sw_breakpoint(void)
+{
+    return 1;
+}
+
+static int kvm_handle_debug(PowerPCCPU *cpu, struct kvm_run *run)
+{
+    CPUState *cs = CPU(cpu);
+    CPUPPCState *env = &cpu->env;
+    struct kvm_debug_exit_arch *arch_info = &run->debug.arch;
+
+    if (cs->singlestep_enabled) {
+        return kvm_handle_singlestep();
     }
 
-    return handle;
+    if (arch_info->status) {
+        return kvm_handle_hw_breakpoint(cs, arch_info);
+    }
+
+    if (kvm_find_sw_breakpoint(cs, arch_info->address)) {
+        return kvm_handle_sw_breakpoint();
+    }
+
+    /*
+     * QEMU is not able to handle debug exception, so inject
+     * program exception to guest;
+     * Yes program exception NOT debug exception !!
+     * When QEMU is using debug resources then debug exception must
+     * be always set. To achieve this we set MSR_DE and also set
+     * MSRP_DEP so guest cannot change MSR_DE.
+     * When emulating debug resource for guest we want guest
+     * to control MSR_DE (enable/disable debug interrupt on need).
+     * Supporting both configurations are NOT possible.
+     * So the result is that we cannot share debug resources
+     * between QEMU and Guest on BOOKE architecture.
+     * In the current design QEMU gets the priority over guest,
+     * this means that if QEMU is using debug resources then guest
+     * cannot use them;
+     * For software breakpoint QEMU uses a privileged instruction;
+     * So there cannot be any reason that we are here for guest
+     * set debug exception, only possibility is guest executed a
+     * privileged / illegal instruction and that's why we are
+     * injecting a program interrupt.
+     */
+    cpu_synchronize_state(cs);
+    /*
+     * env->nip is PC, so increment this by 4 to use
+     * ppc_cpu_do_interrupt(), which set srr0 = env->nip - 4.
+     */
+    env->nip += 4;
+    cs->exception_index = POWERPC_EXCP_PROGRAM;
+    env->error_code = POWERPC_EXCP_INVAL;
+    ppc_cpu_do_interrupt(cs);
+
+    return 0;
 }
 
 int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
@@ -1927,6 +1954,16 @@ uint64_t kvmppc_get_clockfreq(void)
     return kvmppc_read_int_cpu_dt("clock-frequency");
 }
 
+static int kvmppc_get_dec_bits(void)
+{
+    int nr_bits = kvmppc_read_int_cpu_dt("ibm,dec-bits");
+
+    if (nr_bits > 0) {
+        return nr_bits;
+    }
+    return 0;
+}
+
 static int kvmppc_get_pvinfo(CPUPPCState *env, struct kvm_ppc_pvinfo *pvinfo)
  {
      PowerPCCPU *cpu = ppc_env_get_cpu(env);
@@ -2007,6 +2044,11 @@ void kvmppc_enable_clear_ref_mod_hcalls(void)
     kvmppc_enable_hcall(kvm_state, H_CLEAR_MOD);
 }
 
+void kvmppc_enable_h_page_init(void)
+{
+    kvmppc_enable_hcall(kvm_state, H_PAGE_INIT);
+}
+
 void kvmppc_set_papr(PowerPCCPU *cpu)
 {
     CPUState *cs = CPU(cpu);
@@ -2379,7 +2421,13 @@ static int parse_cap_ppc_safe_bounds_check(struct kvm_ppc_cpu_char c)
 
 static int parse_cap_ppc_safe_indirect_branch(struct kvm_ppc_cpu_char c)
 {
-    if (c.character & c.character_mask & H_CPU_CHAR_CACHE_COUNT_DIS) {
+    if ((~c.behaviour & c.behaviour_mask & H_CPU_BEHAV_FLUSH_COUNT_CACHE) &&
+        (~c.character & c.character_mask & H_CPU_CHAR_CACHE_COUNT_DIS) &&
+        (~c.character & c.character_mask & H_CPU_CHAR_BCCTRL_SERIALISED)) {
+        return SPAPR_CAP_FIXED_NA;
+    } else if (c.behaviour & c.behaviour_mask & H_CPU_BEHAV_FLUSH_COUNT_CACHE) {
+        return SPAPR_CAP_WORKAROUND;
+    } else if (c.character & c.character_mask & H_CPU_CHAR_CACHE_COUNT_DIS) {
         return  SPAPR_CAP_FIXED_CCD;
     } else if (c.character & c.character_mask & H_CPU_CHAR_BCCTRL_SERIALISED) {
         return SPAPR_CAP_FIXED_IBS;
@@ -2388,6 +2436,14 @@ static int parse_cap_ppc_safe_indirect_branch(struct kvm_ppc_cpu_char c)
     return 0;
 }
 
+static int parse_cap_ppc_count_cache_flush_assist(struct kvm_ppc_cpu_char c)
+{
+    if (c.character & c.character_mask & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) {
+        return 1;
+    }
+    return 0;
+}
+
 static void kvmppc_get_cpu_characteristics(KVMState *s)
 {
     struct kvm_ppc_cpu_char c;
@@ -2410,6 +2466,8 @@ static void kvmppc_get_cpu_characteristics(KVMState *s)
     cap_ppc_safe_cache = parse_cap_ppc_safe_cache(c);
     cap_ppc_safe_bounds_check = parse_cap_ppc_safe_bounds_check(c);
     cap_ppc_safe_indirect_branch = parse_cap_ppc_safe_indirect_branch(c);
+    cap_ppc_count_cache_flush_assist =
+        parse_cap_ppc_count_cache_flush_assist(c);
 }
 
 int kvmppc_get_cap_safe_cache(void)
@@ -2427,6 +2485,11 @@ int kvmppc_get_cap_safe_indirect_branch(void)
     return cap_ppc_safe_indirect_branch;
 }
 
+int kvmppc_get_cap_count_cache_flush_assist(void)
+{
+    return cap_ppc_count_cache_flush_assist;
+}
+
 bool kvmppc_has_cap_nested_kvm_hv(void)
 {
     return !!cap_ppc_nested_kvm_hv;
@@ -2442,6 +2505,35 @@ bool kvmppc_has_cap_spapr_vfio(void)
     return cap_spapr_vfio;
 }
 
+int kvmppc_get_cap_large_decr(void)
+{
+    return cap_large_decr;
+}
+
+int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable)
+{
+    CPUState *cs = CPU(cpu);
+    uint64_t lpcr;
+
+    kvm_get_one_reg(cs, KVM_REG_PPC_LPCR_64, &lpcr);
+    /* Do we need to modify the LPCR? */
+    if (!!(lpcr & LPCR_LD) != !!enable) {
+        if (enable) {
+            lpcr |= LPCR_LD;
+        } else {
+            lpcr &= ~LPCR_LD;
+        }
+        kvm_set_one_reg(cs, KVM_REG_PPC_LPCR_64, &lpcr);
+        kvm_get_one_reg(cs, KVM_REG_PPC_LPCR_64, &lpcr);
+
+        if (!!(lpcr & LPCR_LD) != !!enable) {
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
 PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
 {
     uint32_t host_pvr = mfpvr();
diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index bdfaa4e70a..2c2ea30e87 100644
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -23,6 +23,7 @@ int kvmppc_set_interrupt(PowerPCCPU *cpu, int irq, int level);
 void kvmppc_enable_logical_ci_hcalls(void);
 void kvmppc_enable_set_mode_hcall(void);
 void kvmppc_enable_clear_ref_mod_hcalls(void);
+void kvmppc_enable_h_page_init(void);
 void kvmppc_set_papr(PowerPCCPU *cpu);
 int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr);
 void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy);
@@ -62,8 +63,11 @@ bool kvmppc_has_cap_mmu_hash_v3(void);
 int kvmppc_get_cap_safe_cache(void);
 int kvmppc_get_cap_safe_bounds_check(void);
 int kvmppc_get_cap_safe_indirect_branch(void);
+int kvmppc_get_cap_count_cache_flush_assist(void);
 bool kvmppc_has_cap_nested_kvm_hv(void);
 int kvmppc_set_cap_nested_kvm_hv(int enable);
+int kvmppc_get_cap_large_decr(void);
+int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable);
 int kvmppc_enable_hwrng(void);
 int kvmppc_put_books_sregs(PowerPCCPU *cpu);
 PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void);
@@ -135,6 +139,10 @@ static inline void kvmppc_enable_clear_ref_mod_hcalls(void)
 {
 }
 
+static inline void kvmppc_enable_h_page_init(void)
+{
+}
+
 static inline void kvmppc_set_papr(PowerPCCPU *cpu)
 {
 }
@@ -322,6 +330,11 @@ static inline int kvmppc_get_cap_safe_indirect_branch(void)
     return 0;
 }
 
+static inline int kvmppc_get_cap_count_cache_flush_assist(void)
+{
+    return 0;
+}
+
 static inline bool kvmppc_has_cap_nested_kvm_hv(void)
 {
     return false;
@@ -332,6 +345,16 @@ static inline int kvmppc_set_cap_nested_kvm_hv(int enable)
     return -1;
 }
 
+static inline int kvmppc_get_cap_large_decr(void)
+{
+    return 0;
+}
+
+static inline int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable)
+{
+    return -1;
+}
+
 static inline int kvmppc_enable_hwrng(void)
 {
     return -1;
diff --git a/target/ppc/machine.c b/target/ppc/machine.c
index 756b6d2971..a92d0ad3a3 100644
--- a/target/ppc/machine.c
+++ b/target/ppc/machine.c
@@ -150,7 +150,7 @@ static int get_fpr(QEMUFile *f, void *pv, size_t size,
 {
     ppc_vsr_t *v = pv;
 
-    v->u64[0] = qemu_get_be64(f);
+    v->VsrD(0) = qemu_get_be64(f);
 
     return 0;
 }
@@ -160,7 +160,7 @@ static int put_fpr(QEMUFile *f, void *pv, size_t size,
 {
     ppc_vsr_t *v = pv;
 
-    qemu_put_be64(f, v->u64[0]);
+    qemu_put_be64(f, v->VsrD(0));
     return 0;
 }
 
@@ -181,7 +181,7 @@ static int get_vsr(QEMUFile *f, void *pv, size_t size,
 {
     ppc_vsr_t *v = pv;
 
-    v->u64[1] = qemu_get_be64(f);
+    v->VsrD(1) = qemu_get_be64(f);
 
     return 0;
 }
@@ -191,7 +191,7 @@ static int put_vsr(QEMUFile *f, void *pv, size_t size,
 {
     ppc_vsr_t *v = pv;
 
-    qemu_put_be64(f, v->u64[1]);
+    qemu_put_be64(f, v->VsrD(1));
     return 0;
 }
 
diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c
index c431303eff..a2b1ec5040 100644
--- a/target/ppc/mmu-hash64.c
+++ b/target/ppc/mmu-hash64.c
@@ -1109,7 +1109,7 @@ void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val)
     case POWERPC_MMU_3_00: /* P9 */
         lpcr = val & (LPCR_VPM1 | LPCR_ISL | LPCR_KBV | LPCR_DPFD |
                       (LPCR_PECE_U_MASK & LPCR_HVEE) | LPCR_ILE | LPCR_AIL |
-                      LPCR_UPRT | LPCR_EVIRT | LPCR_ONL | LPCR_HR |
+                      LPCR_UPRT | LPCR_EVIRT | LPCR_ONL | LPCR_HR | LPCR_LD |
                       (LPCR_PECE_L_MASK & (LPCR_PDEE | LPCR_HDEE | LPCR_EEE |
                       LPCR_DEE | LPCR_OEE)) | LPCR_MER | LPCR_GTSE | LPCR_TC |
                       LPCR_HEIC | LPCR_LPES0 | LPCR_HVICE | LPCR_HDICE);
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 819221f246..98b37cebc2 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -6677,34 +6677,22 @@ GEN_TM_PRIV_NOOP(trechkpt);
 
 static inline void get_fpr(TCGv_i64 dst, int regno)
 {
-    tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, vsr[regno].u64[0]));
+    tcg_gen_ld_i64(dst, cpu_env, fpr_offset(regno));
 }
 
 static inline void set_fpr(int regno, TCGv_i64 src)
 {
-    tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, vsr[regno].u64[0]));
+    tcg_gen_st_i64(src, cpu_env, fpr_offset(regno));
 }
 
 static inline void get_avr64(TCGv_i64 dst, int regno, bool high)
 {
-#ifdef HOST_WORDS_BIGENDIAN
-    tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState,
-                                          vsr[32 + regno].u64[(high ? 0 : 1)]));
-#else
-    tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState,
-                                          vsr[32 + regno].u64[(high ? 1 : 0)]));
-#endif
+    tcg_gen_ld_i64(dst, cpu_env, avr64_offset(regno, high));
 }
 
 static inline void set_avr64(int regno, TCGv_i64 src, bool high)
 {
-#ifdef HOST_WORDS_BIGENDIAN
-    tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState,
-                                          vsr[32 + regno].u64[(high ? 0 : 1)]));
-#else
-    tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState,
-                                          vsr[32 + regno].u64[(high ? 1 : 0)]));
-#endif
+    tcg_gen_st_i64(src, cpu_env, avr64_offset(regno, high));
 }
 
 #include "translate/fp-impl.inc.c"
@@ -7417,7 +7405,7 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf,
 #if !defined(NO_TIMER_DUMP)
     cpu_fprintf(f, "TB %08" PRIu32 " %08" PRIu64
 #if !defined(CONFIG_USER_ONLY)
-                " DECR %08" PRIu32
+                " DECR " TARGET_FMT_lu
 #endif
                 "\n",
                 cpu_ppc_load_tbu(env), cpu_ppc_load_tbl(env)
diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
index f1b15ae2cb..eb10c533ca 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -10,15 +10,10 @@
 static inline TCGv_ptr gen_avr_ptr(int reg)
 {
     TCGv_ptr r = tcg_temp_new_ptr();
-    tcg_gen_addi_ptr(r, cpu_env, offsetof(CPUPPCState, vsr[32 + reg].u64[0]));
+    tcg_gen_addi_ptr(r, cpu_env, avr_full_offset(reg));
     return r;
 }
 
-static inline long avr64_offset(int reg, bool high)
-{
-    return offsetof(CPUPPCState, vsr[32 + reg].u64[(high ? 0 : 1)]);
-}
-
 #define GEN_VR_LDX(name, opc2, opc3)                                          \
 static void glue(gen_, name)(DisasContext *ctx)                                       \
 {                                                                             \
@@ -205,7 +200,7 @@ static void gen_mtvscr(DisasContext *ctx)
     }
 
     val = tcg_temp_new_i32();
-    bofs = avr64_offset(rB(ctx->opcode), true);
+    bofs = avr_full_offset(rB(ctx->opcode));
 #ifdef HOST_WORDS_BIGENDIAN
     bofs += 3 * 4;
 #endif
@@ -284,9 +279,9 @@ static void glue(gen_, name)(DisasContext *ctx)                         \
     }                                                                   \
                                                                         \
     tcg_op(vece,                                                        \
-           avr64_offset(rD(ctx->opcode), true),                         \
-           avr64_offset(rA(ctx->opcode), true),                         \
-           avr64_offset(rB(ctx->opcode), true),                         \
+           avr_full_offset(rD(ctx->opcode)),                            \
+           avr_full_offset(rA(ctx->opcode)),                            \
+           avr_full_offset(rB(ctx->opcode)),                            \
            16, 16);                                                     \
 }
 
@@ -578,10 +573,10 @@ static void glue(gen_, NAME)(DisasContext *ctx)                         \
         gen_exception(ctx, POWERPC_EXCP_VPU);                           \
         return;                                                         \
     }                                                                   \
-    tcg_gen_gvec_4(avr64_offset(rD(ctx->opcode), true),                 \
+    tcg_gen_gvec_4(avr_full_offset(rD(ctx->opcode)),                    \
                    offsetof(CPUPPCState, vscr_sat),                     \
-                   avr64_offset(rA(ctx->opcode), true),                 \
-                   avr64_offset(rB(ctx->opcode), true),                 \
+                   avr_full_offset(rA(ctx->opcode)),                    \
+                   avr_full_offset(rB(ctx->opcode)),                    \
                    16, 16, &g);                                         \
 }
 
@@ -755,7 +750,7 @@ static void glue(gen_, name)(DisasContext *ctx)                         \
             return;                                                     \
         }                                                               \
         simm = SIMM5(ctx->opcode);                                      \
-        tcg_op(avr64_offset(rD(ctx->opcode), true), 16, 16, simm);      \
+        tcg_op(avr_full_offset(rD(ctx->opcode)), 16, 16, simm);         \
     }
 
 GEN_VXFORM_DUPI(vspltisb, tcg_gen_gvec_dup8i, 6, 12);
@@ -850,8 +845,8 @@ static void gen_vsplt(DisasContext *ctx, int vece)
     }
 
     uimm = UIMM5(ctx->opcode);
-    bofs = avr64_offset(rB(ctx->opcode), true);
-    dofs = avr64_offset(rD(ctx->opcode), true);
+    bofs = avr_full_offset(rB(ctx->opcode));
+    dofs = avr_full_offset(rD(ctx->opcode));
 
     /* Experimental testing shows that hardware masks the immediate.  */
     bofs += (uimm << vece) & 15;
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index e73197e717..508e9199c8 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1,54 +1,23 @@
 /***                           VSX extension                               ***/
 
-static inline void get_vsr(TCGv_i64 dst, int n)
-{
-    tcg_gen_ld_i64(dst, cpu_env, offsetof(CPUPPCState, vsr[n].u64[1]));
-}
-
-static inline void set_vsr(int n, TCGv_i64 src)
-{
-    tcg_gen_st_i64(src, cpu_env, offsetof(CPUPPCState, vsr[n].u64[1]));
-}
-
-static inline int vsr_full_offset(int n)
-{
-    return offsetof(CPUPPCState, vsr[n].u64[0]);
-}
-
 static inline void get_cpu_vsrh(TCGv_i64 dst, int n)
 {
-    if (n < 32) {
-        get_fpr(dst, n);
-    } else {
-        get_avr64(dst, n - 32, true);
-    }
+    tcg_gen_ld_i64(dst, cpu_env, vsr64_offset(n, true));
 }
 
 static inline void get_cpu_vsrl(TCGv_i64 dst, int n)
 {
-    if (n < 32) {
-        get_vsr(dst, n);
-    } else {
-        get_avr64(dst, n - 32, false);
-    }
+    tcg_gen_ld_i64(dst, cpu_env, vsr64_offset(n, false));
 }
 
 static inline void set_cpu_vsrh(int n, TCGv_i64 src)
 {
-    if (n < 32) {
-        set_fpr(n, src);
-    } else {
-        set_avr64(n - 32, src, true);
-    }
+    tcg_gen_st_i64(src, cpu_env, vsr64_offset(n, true));
 }
 
 static inline void set_cpu_vsrl(int n, TCGv_i64 src)
 {
-    if (n < 32) {
-        set_vsr(n, src);
-    } else {
-        set_avr64(n - 32, src, false);
-    }
+    tcg_gen_st_i64(src, cpu_env, vsr64_offset(n, false));
 }
 
 #define VSX_LOAD_SCALAR(name, operation)                      \
@@ -1618,8 +1587,7 @@ static void gen_xsxsigdp(DisasContext *ctx)
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
     get_cpu_vsrh(t1, xB(ctx->opcode));
-    tcg_gen_andi_i64(rt, t1, 0x000FFFFFFFFFFFFF);
-    tcg_gen_or_i64(rt, rt, t0);
+    tcg_gen_deposit_i64(rt, t0, t1, 0, 52);
 
     tcg_temp_free_i64(t0);
     tcg_temp_free_i64(t1);
@@ -1655,8 +1623,7 @@ static void gen_xsxsigqp(DisasContext *ctx)
     tcg_gen_movi_i64(t0, 0x0001000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
-    tcg_gen_andi_i64(xth, xbh, 0x0000FFFFFFFFFFFF);
-    tcg_gen_or_i64(xth, xth, t0);
+    tcg_gen_deposit_i64(xth, t0, xbh, 0, 48);
     set_cpu_vsrh(rD(ctx->opcode) + 32, xth);
     tcg_gen_mov_i64(xtl, xbl);
     set_cpu_vsrl(rD(ctx->opcode) + 32, xtl);
@@ -1726,7 +1693,6 @@ static void gen_xviexpdp(DisasContext *ctx)
     TCGv_i64 xal;
     TCGv_i64 xbh;
     TCGv_i64 xbl;
-    TCGv_i64 t0;
 
     if (unlikely(!ctx->vsx_enabled)) {
         gen_exception(ctx, POWERPC_EXCP_VSXU);
@@ -1742,20 +1708,13 @@ static void gen_xviexpdp(DisasContext *ctx)
     get_cpu_vsrl(xal, xA(ctx->opcode));
     get_cpu_vsrh(xbh, xB(ctx->opcode));
     get_cpu_vsrl(xbl, xB(ctx->opcode));
-    t0 = tcg_temp_new_i64();
 
-    tcg_gen_andi_i64(xth, xah, 0x800FFFFFFFFFFFFF);
-    tcg_gen_andi_i64(t0, xbh, 0x7FF);
-    tcg_gen_shli_i64(t0, t0, 52);
-    tcg_gen_or_i64(xth, xth, t0);
+    tcg_gen_deposit_i64(xth, xah, xbh, 52, 11);
     set_cpu_vsrh(xT(ctx->opcode), xth);
-    tcg_gen_andi_i64(xtl, xal, 0x800FFFFFFFFFFFFF);
-    tcg_gen_andi_i64(t0, xbl, 0x7FF);
-    tcg_gen_shli_i64(t0, t0, 52);
-    tcg_gen_or_i64(xtl, xtl, t0);
+
+    tcg_gen_deposit_i64(xtl, xal, xbl, 52, 11);
     set_cpu_vsrl(xT(ctx->opcode), xtl);
 
-    tcg_temp_free_i64(t0);
     tcg_temp_free_i64(xth);
     tcg_temp_free_i64(xtl);
     tcg_temp_free_i64(xah);
@@ -1853,16 +1812,14 @@ static void gen_xvxsigdp(DisasContext *ctx)
     tcg_gen_movi_i64(t0, 0x0010000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
-    tcg_gen_andi_i64(xth, xbh, 0x000FFFFFFFFFFFFF);
-    tcg_gen_or_i64(xth, xth, t0);
+    tcg_gen_deposit_i64(xth, t0, xbh, 0, 52);
     set_cpu_vsrh(xT(ctx->opcode), xth);
 
     tcg_gen_extract_i64(exp, xbl, 52, 11);
     tcg_gen_movi_i64(t0, 0x0010000000000000);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0);
     tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0);
-    tcg_gen_andi_i64(xtl, xbl, 0x000FFFFFFFFFFFFF);
-    tcg_gen_or_i64(xtl, xtl, t0);
+    tcg_gen_deposit_i64(xth, t0, xbl, 0, 52);
     set_cpu_vsrl(xT(ctx->opcode), xtl);
 
     tcg_temp_free_i64(t0);
diff --git a/target/ppc/translate_init.inc.c b/target/ppc/translate_init.inc.c
index 58542c0fe0..0bd555eb19 100644
--- a/target/ppc/translate_init.inc.c
+++ b/target/ppc/translate_init.inc.c
@@ -8376,6 +8376,7 @@ POWERPC_FAMILY(POWER5P)(ObjectClass *oc, void *data)
 #if defined(CONFIG_SOFTMMU)
     pcc->handle_mmu_fault = ppc_hash64_handle_mmu_fault;
     pcc->hash64_opts = &ppc_hash64_opts_basic;
+    pcc->lrg_decr_bits = 32;
 #endif
     pcc->excp_model = POWERPC_EXCP_970;
     pcc->bus_model = PPC_FLAGS_INPUT_970;
@@ -8550,6 +8551,7 @@ POWERPC_FAMILY(POWER7)(ObjectClass *oc, void *data)
 #if defined(CONFIG_SOFTMMU)
     pcc->handle_mmu_fault = ppc_hash64_handle_mmu_fault;
     pcc->hash64_opts = &ppc_hash64_opts_POWER7;
+    pcc->lrg_decr_bits = 32;
 #endif
     pcc->excp_model = POWERPC_EXCP_POWER7;
     pcc->bus_model = PPC_FLAGS_INPUT_POWER7;
@@ -8718,6 +8720,7 @@ POWERPC_FAMILY(POWER8)(ObjectClass *oc, void *data)
 #if defined(CONFIG_SOFTMMU)
     pcc->handle_mmu_fault = ppc_hash64_handle_mmu_fault;
     pcc->hash64_opts = &ppc_hash64_opts_POWER7;
+    pcc->lrg_decr_bits = 32;
 #endif
     pcc->excp_model = POWERPC_EXCP_POWER8;
     pcc->bus_model = PPC_FLAGS_INPUT_POWER7;
@@ -8892,7 +8895,7 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data)
                        PPC_CACHE | PPC_CACHE_ICBI | PPC_CACHE_DCBZ |
                        PPC_MEM_SYNC | PPC_MEM_EIEIO |
                        PPC_MEM_TLBSYNC |
-                       PPC_64B | PPC_64BX | PPC_ALTIVEC |
+                       PPC_64B | PPC_64H | PPC_64BX | PPC_ALTIVEC |
                        PPC_SEGMENT_64B | PPC_SLBI |
                        PPC_POPCNTB | PPC_POPCNTWD |
                        PPC_CILDST;
@@ -8904,6 +8907,7 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data)
                         PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 |
                         PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL;
     pcc->msr_mask = (1ull << MSR_SF) |
+                    (1ull << MSR_SHV) |
                     (1ull << MSR_TM) |
                     (1ull << MSR_VR) |
                     (1ull << MSR_VSX) |
@@ -8926,6 +8930,7 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data)
     /* segment page size remain the same */
     pcc->hash64_opts = &ppc_hash64_opts_POWER7;
     pcc->radix_page_info = &POWER9_radix_page_info;
+    pcc->lrg_decr_bits = 56;
 #endif
     pcc->excp_model = POWERPC_EXCP_POWER9;
     pcc->bus_model = PPC_FLAGS_INPUT_POWER9;