Base patches for MTTCG enablement.

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQExBAABCAAbBQJYF07FFBxwYm9uemluaUByZWRoYXQuY29tAAoJEL/70l94x66D
 ppoIAI4AxWocso5WIUH6uEHjOAxw9ZNhZ92nF8VtcbvGtN/eh8Qk4jfRX+W/Jl0q
 D13Rm3m8ynNHqh8YFs+O6i/WSgxHGxKwb75mNr36HDnYnMFluTvRQkvYJUXRyRuL
 CVtNgy8+q8FbbWo+NiJ5I7gfk2Si4BQfZN0uCLqGuCwqvvA/spN13xUcpeBXEKhL
 TeDGZBT/atDnT2bRcve8E8g5/0RKjTL9EB0jwfJjHocT5bs+toPe6js9VnZDRNWN
 ZldcONgEHj3zAj9j7hTkVWFTGPSCx/tt6y6JeORq1oxk0mCCswEk0U9A3hLzLjc/
 94XHsLaEoZ7HNAKtkLc07NYhkQM=
 =+6Sj
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream-mttcg' into staging

Base patches for MTTCG enablement.

# gpg: Signature made Mon 31 Oct 2016 14:01:41 GMT
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream-mttcg:
  tcg: move locking for tb_invalidate_phys_page_range up
  *_run_on_cpu: introduce run_on_cpu_data type
  cpus: re-factor out handle_icount_deadline
  tcg: cpus rm tcg_exec_all()
  tcg: move tcg_exec_all and helpers above thread fn
  target-arm/arm-powerctl: wake up sleeping CPUs
  tcg: protect translation related stuff with tb_lock.
  translate-all: Add assert_(memory|tb)_lock annotations
  linux-user/elfload: ensure mmap_lock() held while setting up
  tcg: comment on which functions have to be called with tb_lock held
  cpu-exec: include cpu_index in CPU_LOG_EXEC messages
  translate-all: add DEBUG_LOCKING asserts
  translate_all: DEBUG_FLUSH -> DEBUG_TB_FLUSH
  cpus: make all_vcpus_paused() return bool

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

bsd-user/mmap.c

@@ -42,6 +42,11 @@ void mmap_unlock(void)
     }
 }
 
+bool have_mmap_lock(void)
+{
+    return mmap_lock_count > 0 ? true : false;
+}
+
 /* Grab lock to make sure things are in a consistent state after fork().  */
 void mmap_fork_start(void)
 {

cpu-exec.c

@@ -143,8 +143,9 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
     uint8_t *tb_ptr = itb->tc_ptr;
 
     qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
-                           "Trace %p [" TARGET_FMT_lx "] %s\n",
+                           "Trace %p [%d: " TARGET_FMT_lx "] %s\n",
-                           itb->tc_ptr, itb->pc, lookup_symbol(itb->pc));
+                           itb->tc_ptr, cpu->cpu_index, itb->pc,
+                           lookup_symbol(itb->pc));
 
 #if defined(DEBUG_DISAS)
     if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
@@ -204,15 +205,21 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
     if (max_cycles > CF_COUNT_MASK)
         max_cycles = CF_COUNT_MASK;
 
+    tb_lock();
     tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                      max_cycles | CF_NOCACHE
                          | (ignore_icount ? CF_IGNORE_ICOUNT : 0));
     tb->orig_tb = orig_tb;
+    tb_unlock();
+
     /* execute the generated code */
     trace_exec_tb_nocache(tb, tb->pc);
     cpu_tb_exec(cpu, tb);
+
+    tb_lock();
     tb_phys_invalidate(tb, -1);
     tb_free(tb);
+    tb_unlock();
 }
 #endif
 

cpus-common.c

@@ -109,7 +109,7 @@ void cpu_list_remove(CPUState *cpu)
 struct qemu_work_item {
     struct qemu_work_item *next;
     run_on_cpu_func func;
-    void *data;
+    run_on_cpu_data data;
     bool free, exclusive, done;
 };
 
@@ -129,7 +129,7 @@ static void queue_work_on_cpu(CPUState *cpu, struct qemu_work_item *wi)
     qemu_cpu_kick(cpu);
 }
 
-void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data,
+void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data,
                    QemuMutex *mutex)
 {
     struct qemu_work_item wi;
@@ -154,7 +154,7 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data,
     }
 }
 
-void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data)
+void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data)
 {
     struct qemu_work_item *wi;
 
@@ -296,7 +296,8 @@ void cpu_exec_end(CPUState *cpu)
     }
 }
 
-void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data)
+void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func,
+                           run_on_cpu_data data)
 {
     struct qemu_work_item *wi;
 

cpus.c

@@ -69,7 +69,6 @@
 
 #endif /* CONFIG_LINUX */
 
-static CPUState *next_cpu;
 int64_t max_delay;
 int64_t max_advance;
 
@@ -557,7 +556,7 @@ static const VMStateDescription vmstate_timers = {
     }
 };
 
-static void cpu_throttle_thread(CPUState *cpu, void *opaque)
+static void cpu_throttle_thread(CPUState *cpu, run_on_cpu_data opaque)
 {
     double pct;
     double throttle_ratio;
@@ -588,7 +587,8 @@ static void cpu_throttle_timer_tick(void *opaque)
     }
     CPU_FOREACH(cpu) {
         if (!atomic_xchg(&cpu->throttle_thread_scheduled, 1)) {
-            async_run_on_cpu(cpu, cpu_throttle_thread, NULL);
+            async_run_on_cpu(cpu, cpu_throttle_thread,
+                             RUN_ON_CPU_NULL);
         }
     }
 
@@ -915,7 +915,7 @@ void qemu_init_cpu_loop(void)
     qemu_thread_get_self(&io_thread);
 }
 
-void run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data)
+void run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data)
 {
     do_run_on_cpu(cpu, func, data, &qemu_global_mutex);
 }
@@ -1055,12 +1055,102 @@ static void *qemu_dummy_cpu_thread_fn(void *arg)
 #endif
 }
 
-static void tcg_exec_all(void);
+static int64_t tcg_get_icount_limit(void)
+{
+    int64_t deadline;
+
+    if (replay_mode != REPLAY_MODE_PLAY) {
+        deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
+
+        /* Maintain prior (possibly buggy) behaviour where if no deadline
+         * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
+         * INT32_MAX nanoseconds ahead, we still use INT32_MAX
+         * nanoseconds.
+         */
+        if ((deadline < 0) || (deadline > INT32_MAX)) {
+            deadline = INT32_MAX;
+        }
+
+        return qemu_icount_round(deadline);
+    } else {
+        return replay_get_instructions();
+    }
+}
+
+static void handle_icount_deadline(void)
+{
+    if (use_icount) {
+        int64_t deadline =
+            qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
+
+        if (deadline == 0) {
+            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+        }
+    }
+}
+
+static int tcg_cpu_exec(CPUState *cpu)
+{
+    int ret;
+#ifdef CONFIG_PROFILER
+    int64_t ti;
+#endif
+
+#ifdef CONFIG_PROFILER
+    ti = profile_getclock();
+#endif
+    if (use_icount) {
+        int64_t count;
+        int decr;
+        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
+                                    + cpu->icount_extra);
+        cpu->icount_decr.u16.low = 0;
+        cpu->icount_extra = 0;
+        count = tcg_get_icount_limit();
+        timers_state.qemu_icount += count;
+        decr = (count > 0xffff) ? 0xffff : count;
+        count -= decr;
+        cpu->icount_decr.u16.low = decr;
+        cpu->icount_extra = count;
+    }
+    cpu_exec_start(cpu);
+    ret = cpu_exec(cpu);
+    cpu_exec_end(cpu);
+#ifdef CONFIG_PROFILER
+    tcg_time += profile_getclock() - ti;
+#endif
+    if (use_icount) {
+        /* Fold pending instructions back into the
+           instruction counter, and clear the interrupt flag.  */
+        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
+                        + cpu->icount_extra);
+        cpu->icount_decr.u32 = 0;
+        cpu->icount_extra = 0;
+        replay_account_executed_instructions();
+    }
+    return ret;
+}
+
+/* Destroy any remaining vCPUs which have been unplugged and have
+ * finished running
+ */
+static void deal_with_unplugged_cpus(void)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        if (cpu->unplug && !cpu_can_run(cpu)) {
+            qemu_tcg_destroy_vcpu(cpu);
+            cpu->created = false;
+            qemu_cond_signal(&qemu_cpu_cond);
+            break;
+        }
+    }
+}
 
 static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
     CPUState *cpu = arg;
-    CPUState *remove_cpu = NULL;
 
     rcu_register_thread();
 
@@ -1087,29 +1177,44 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
     /* process any pending work */
     atomic_mb_set(&exit_request, 1);
 
+    cpu = first_cpu;
+
     while (1) {
-        tcg_exec_all();
+        /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
+        qemu_account_warp_timer();
 
-        if (use_icount) {
+        if (!cpu) {
-            int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
+            cpu = first_cpu;
+        }
 
-            if (deadline == 0) {
+        for (; cpu != NULL && !exit_request; cpu = CPU_NEXT(cpu)) {
-                qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+
-            }
+            qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
-        }
+                              (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
-        qemu_tcg_wait_io_event(QTAILQ_FIRST(&cpus));
+
-        CPU_FOREACH(cpu) {
+            if (cpu_can_run(cpu)) {
-            if (cpu->unplug && !cpu_can_run(cpu)) {
+                int r;
-                remove_cpu = cpu;
+                r = tcg_cpu_exec(cpu);
+                if (r == EXCP_DEBUG) {
+                    cpu_handle_guest_debug(cpu);
                     break;
                 }
+            } else if (cpu->stop || cpu->stopped) {
+                if (cpu->unplug) {
+                    cpu = CPU_NEXT(cpu);
                 }
-        if (remove_cpu) {
+                break;
-            qemu_tcg_destroy_vcpu(remove_cpu);
-            cpu->created = false;
-            qemu_cond_signal(&qemu_cpu_cond);
-            remove_cpu = NULL;
             }
+
+        } /* for cpu.. */
+
+        /* Pairs with smp_wmb in qemu_cpu_kick.  */
+        atomic_mb_set(&exit_request, 0);
+
+        handle_icount_deadline();
+
+        qemu_tcg_wait_io_event(QTAILQ_FIRST(&cpus));
+        deal_with_unplugged_cpus();
     }
 
     return NULL;
@@ -1207,17 +1312,17 @@ void qemu_mutex_unlock_iothread(void)
     qemu_mutex_unlock(&qemu_global_mutex);
 }
 
-static int all_vcpus_paused(void)
+static bool all_vcpus_paused(void)
 {
     CPUState *cpu;
 
     CPU_FOREACH(cpu) {
         if (!cpu->stopped) {
-            return 0;
+            return false;
         }
     }
 
-    return 1;
+    return true;
 }
 
 void pause_all_vcpus(void)
@@ -1412,106 +1517,6 @@ int vm_stop_force_state(RunState state)
     }
 }
 
-static int64_t tcg_get_icount_limit(void)
-{
-    int64_t deadline;
-
-    if (replay_mode != REPLAY_MODE_PLAY) {
-        deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
-
-        /* Maintain prior (possibly buggy) behaviour where if no deadline
-         * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
-         * INT32_MAX nanoseconds ahead, we still use INT32_MAX
-         * nanoseconds.
-         */
-        if ((deadline < 0) || (deadline > INT32_MAX)) {
-            deadline = INT32_MAX;
-        }
-
-        return qemu_icount_round(deadline);
-    } else {
-        return replay_get_instructions();
-    }
-}
-
-static int tcg_cpu_exec(CPUState *cpu)
-{
-    int ret;
-#ifdef CONFIG_PROFILER
-    int64_t ti;
-#endif
-
-#ifdef CONFIG_PROFILER
-    ti = profile_getclock();
-#endif
-    if (use_icount) {
-        int64_t count;
-        int decr;
-        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
-                                    + cpu->icount_extra);
-        cpu->icount_decr.u16.low = 0;
-        cpu->icount_extra = 0;
-        count = tcg_get_icount_limit();
-        timers_state.qemu_icount += count;
-        decr = (count > 0xffff) ? 0xffff : count;
-        count -= decr;
-        cpu->icount_decr.u16.low = decr;
-        cpu->icount_extra = count;
-    }
-    cpu_exec_start(cpu);
-    ret = cpu_exec(cpu);
-    cpu_exec_end(cpu);
-#ifdef CONFIG_PROFILER
-    tcg_time += profile_getclock() - ti;
-#endif
-    if (use_icount) {
-        /* Fold pending instructions back into the
-           instruction counter, and clear the interrupt flag.  */
-        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
-                        + cpu->icount_extra);
-        cpu->icount_decr.u32 = 0;
-        cpu->icount_extra = 0;
-        replay_account_executed_instructions();
-    }
-    return ret;
-}
-
-static void tcg_exec_all(void)
-{
-    int r;
-
-    /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
-    qemu_account_warp_timer();
-
-    if (next_cpu == NULL) {
-        next_cpu = first_cpu;
-    }
-    for (; next_cpu != NULL && !exit_request; next_cpu = CPU_NEXT(next_cpu)) {
-        CPUState *cpu = next_cpu;
-
-        qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
-                          (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
-
-        if (cpu_can_run(cpu)) {
-            r = tcg_cpu_exec(cpu);
-            if (r == EXCP_DEBUG) {
-                cpu_handle_guest_debug(cpu);
-                break;
-            } else if (r == EXCP_ATOMIC) {
-                cpu_exec_step_atomic(cpu);
-            }
-        } else if (cpu->stop || cpu->stopped) {
-            if (cpu->unplug) {
-                next_cpu = CPU_NEXT(cpu);
-            }
-            break;
-        }
-    }
-
-    /* Pairs with smp_wmb in qemu_cpu_kick.  */
-    atomic_mb_set(&exit_request, 0);
-}
-
 void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
 {
     /* XXX: implement xxx_cpu_list for targets that still miss it */

exec.c

@@ -687,7 +687,11 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp)
 #if defined(CONFIG_USER_ONLY)
 static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
 {
+    mmap_lock();
+    tb_lock();
     tb_invalidate_phys_page_range(pc, pc + 1, 0);
+    tb_unlock();
+    mmap_unlock();
 }
 #else
 static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
@@ -696,6 +700,7 @@ static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
     hwaddr phys = cpu_get_phys_page_attrs_debug(cpu, pc, &attrs);
     int asidx = cpu_asidx_from_attrs(cpu, attrs);
     if (phys != -1) {
+        /* Locks grabbed by tb_invalidate_phys_addr */
         tb_invalidate_phys_addr(cpu->cpu_ases[asidx].as,
                                 phys | (pc & ~TARGET_PAGE_MASK));
     }
@@ -1988,7 +1993,11 @@ ram_addr_t qemu_ram_addr_from_host(void *ptr)
 static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
                                uint64_t val, unsigned size)
 {
+    bool locked = false;
+
     if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) {
+        locked = true;
+        tb_lock();
         tb_invalidate_phys_page_fast(ram_addr, size);
     }
     switch (size) {
@@ -2004,6 +2013,11 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     default:
         abort();
     }
+
+    if (locked) {
+        tb_unlock();
+    }
+
     /* Set both VGA and migration bits for simplicity and to remove
      * the notdirty callback faster.
      */
@@ -2064,6 +2078,12 @@ static void check_watchpoint(int offset, int len, MemTxAttrs attrs, int flags)
                     continue;
                 }
                 cpu->watchpoint_hit = wp;
+
+                /* The tb_lock will be reset when cpu_loop_exit or
+                 * cpu_loop_exit_noexc longjmp back into the cpu_exec
+                 * main loop.
+                 */
+                tb_lock();
                 tb_check_watchpoint(cpu);
                 if (wp->flags & BP_STOP_BEFORE_ACCESS) {
                     cpu->exception_index = EXCP_DEBUG;
@@ -2471,7 +2491,9 @@ static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr,
             cpu_physical_memory_range_includes_clean(addr, length, dirty_log_mask);
     }
     if (dirty_log_mask & (1 << DIRTY_MEMORY_CODE)) {
+        tb_lock();
         tb_invalidate_phys_range(addr, addr + length);
+        tb_unlock();
         dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE);
     }
     cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask);

hw/i386/kvm/apic.c

@@ -133,9 +133,9 @@ static void kvm_apic_vapic_base_update(APICCommonState *s)
     }
 }
 
-static void kvm_apic_put(CPUState *cs, void *data)
+static void kvm_apic_put(CPUState *cs, run_on_cpu_data data)
 {
-    APICCommonState *s = data;
+    APICCommonState *s = data.host_ptr;
     struct kvm_lapic_state kapic;
     int ret;
 
@@ -151,12 +151,12 @@ static void kvm_apic_put(CPUState *cs, void *data)
 
 static void kvm_apic_post_load(APICCommonState *s)
 {
-    run_on_cpu(CPU(s->cpu), kvm_apic_put, s);
+    run_on_cpu(CPU(s->cpu), kvm_apic_put, RUN_ON_CPU_HOST_PTR(s));
 }
 
-static void do_inject_external_nmi(CPUState *cpu, void *data)
+static void do_inject_external_nmi(CPUState *cpu, run_on_cpu_data data)
 {
-    APICCommonState *s = data;
+    APICCommonState *s = data.host_ptr;
     uint32_t lvt;
     int ret;
 
@@ -174,7 +174,7 @@ static void do_inject_external_nmi(CPUState *cpu, void *data)
 
 static void kvm_apic_external_nmi(APICCommonState *s)
 {
-    run_on_cpu(CPU(s->cpu), do_inject_external_nmi, s);
+    run_on_cpu(CPU(s->cpu), do_inject_external_nmi, RUN_ON_CPU_HOST_PTR(s));
 }
 
 static void kvm_send_msi(MSIMessage *msg)
@@ -213,7 +213,7 @@ static void kvm_apic_reset(APICCommonState *s)
     /* Not used by KVM, which uses the CPU mp_state instead.  */
     s->wait_for_sipi = 0;
 
-    run_on_cpu(CPU(s->cpu), kvm_apic_put, s);
+    run_on_cpu(CPU(s->cpu), kvm_apic_put, RUN_ON_CPU_HOST_PTR(s));
 }
 
 static void kvm_apic_realize(DeviceState *dev, Error **errp)

hw/i386/kvmvapic.c

@@ -17,6 +17,7 @@
 #include "sysemu/kvm.h"
 #include "hw/i386/apic_internal.h"
 #include "hw/sysbus.h"
+#include "tcg/tcg.h"
 
 #define VAPIC_IO_PORT           0x7e
 
@@ -449,6 +450,9 @@ static void patch_instruction(VAPICROMState *s, X86CPU *cpu, target_ulong ip)
     resume_all_vcpus();
 
     if (!kvm_enabled()) {
+        /* tb_lock will be reset when cpu_loop_exit_noexc longjmps
+         * back into the cpu_exec loop. */
+        tb_lock();
         tb_gen_code(cs, current_pc, current_cs_base, current_flags, 1);
         cpu_loop_exit_noexc(cs);
     }
@@ -483,10 +487,9 @@ typedef struct VAPICEnableTPRReporting {
     bool enable;
 } VAPICEnableTPRReporting;
 
-static void vapic_do_enable_tpr_reporting(CPUState *cpu, void *data)
+static void vapic_do_enable_tpr_reporting(CPUState *cpu, run_on_cpu_data data)
 {
-    VAPICEnableTPRReporting *info = data;
+    VAPICEnableTPRReporting *info = data.host_ptr;
-
     apic_enable_tpr_access_reporting(info->apic, info->enable);
 }
 
@@ -501,7 +504,7 @@ static void vapic_enable_tpr_reporting(bool enable)
     CPU_FOREACH(cs) {
         cpu = X86_CPU(cs);
         info.apic = cpu->apic_state;
-        run_on_cpu(cs, vapic_do_enable_tpr_reporting, &info);
+        run_on_cpu(cs, vapic_do_enable_tpr_reporting, RUN_ON_CPU_HOST_PTR(&info));
     }
 }
 
@@ -734,9 +737,9 @@ static void vapic_realize(DeviceState *dev, Error **errp)
     nb_option_roms++;
 }
 
-static void do_vapic_enable(CPUState *cs, void *data)
+static void do_vapic_enable(CPUState *cs, run_on_cpu_data data)
 {
-    VAPICROMState *s = data;
+    VAPICROMState *s = data.host_ptr;
     X86CPU *cpu = X86_CPU(cs);
 
     static const uint8_t enabled = 1;
@@ -758,7 +761,7 @@ static void kvmvapic_vm_state_change(void *opaque, int running,
 
     if (s->state == VAPIC_ACTIVE) {
         if (smp_cpus == 1) {
-            run_on_cpu(first_cpu, do_vapic_enable, s);
+            run_on_cpu(first_cpu, do_vapic_enable, RUN_ON_CPU_HOST_PTR(s));
         } else {
             zero = g_malloc0(s->rom_state.vapic_size);
             cpu_physical_memory_write(s->vapic_paddr, zero,

hw/ppc/ppce500_spin.c

@@ -84,11 +84,11 @@ static void mmubooke_create_initial_mapping(CPUPPCState *env,
     env->tlb_dirty = true;
 }
 
-static void spin_kick(CPUState *cs, void *data)
+static void spin_kick(CPUState *cs, run_on_cpu_data data)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
     CPUPPCState *env = &cpu->env;
-    SpinInfo *curspin = data;
+    SpinInfo *curspin = data.host_ptr;
     hwaddr map_size = 64 * 1024 * 1024;
     hwaddr map_start;
 
@@ -147,7 +147,7 @@ static void spin_write(void *opaque, hwaddr addr, uint64_t value,
 
     if (!(ldq_p(&curspin->addr) & 1)) {
         /* run CPU */
-        run_on_cpu(cpu, spin_kick, curspin);
+        run_on_cpu(cpu, spin_kick, RUN_ON_CPU_HOST_PTR(curspin));
     }
 }
 

hw/ppc/spapr.c

@@ -2186,7 +2186,7 @@ static void spapr_machine_finalizefn(Object *obj)
     g_free(spapr->kvm_type);
 }
 
-static void ppc_cpu_do_nmi_on_cpu(CPUState *cs, void *arg)
+static void ppc_cpu_do_nmi_on_cpu(CPUState *cs, run_on_cpu_data arg)
 {
     cpu_synchronize_state(cs);
     ppc_cpu_do_system_reset(cs);
@@ -2197,7 +2197,7 @@ static void spapr_nmi(NMIState *n, int cpu_index, Error **errp)
     CPUState *cs;
 
     CPU_FOREACH(cs) {
-        async_run_on_cpu(cs, ppc_cpu_do_nmi_on_cpu, NULL);
+        async_run_on_cpu(cs, ppc_cpu_do_nmi_on_cpu, RUN_ON_CPU_NULL);
     }
 }
 

hw/ppc/spapr_hcall.c

@@ -19,9 +19,9 @@ struct SPRSyncState {
     target_ulong mask;
 };
 
-static void do_spr_sync(CPUState *cs, void *arg)
+static void do_spr_sync(CPUState *cs, run_on_cpu_data arg)
 {
-    struct SPRSyncState *s = arg;
+    struct SPRSyncState *s = arg.host_ptr;
     PowerPCCPU *cpu = POWERPC_CPU(cs);
     CPUPPCState *env = &cpu->env;
 
@@ -38,7 +38,7 @@ static void set_spr(CPUState *cs, int spr, target_ulong value,
         .value = value,
         .mask = mask
     };
-    run_on_cpu(cs, do_spr_sync, &s);
+    run_on_cpu(cs, do_spr_sync, RUN_ON_CPU_HOST_PTR(&s));
 }
 
 static bool has_spr(PowerPCCPU *cpu, int spr)
@@ -886,10 +886,10 @@ typedef struct {
     Error *err;
 } SetCompatState;
 
-static void do_set_compat(CPUState *cs, void *arg)
+static void do_set_compat(CPUState *cs, run_on_cpu_data arg)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
-    SetCompatState *s = arg;
+    SetCompatState *s = arg.host_ptr;
 
     cpu_synchronize_state(cs);
     ppc_set_compat(cpu, s->cpu_version, &s->err);
@@ -990,7 +990,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu_,
                 .err = NULL,
             };
 
-            run_on_cpu(cs, do_set_compat, &s);
+            run_on_cpu(cs, do_set_compat, RUN_ON_CPU_HOST_PTR(&s));
 
             if (s.err) {
                 error_report_err(s.err);

include/exec/exec-all.h

@@ -316,6 +316,7 @@ static inline void tb_set_jmp_target(TranslationBlock *tb,
 
 #endif
 
+/* Called with tb_lock held.  */
 static inline void tb_add_jump(TranslationBlock *tb, int n,
                                TranslationBlock *tb_next)
 {
@@ -369,6 +370,7 @@ void tlb_fill(CPUState *cpu, target_ulong addr, MMUAccessType access_type,
 #if defined(CONFIG_USER_ONLY)
 void mmap_lock(void);
 void mmap_unlock(void);
+bool have_mmap_lock(void);
 
 static inline tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
 {

include/qom/cpu.h

@@ -231,7 +231,25 @@ struct kvm_run;
 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS)
 
 /* work queue */
-typedef void (*run_on_cpu_func)(CPUState *cpu, void *data);
+
+/* The union type allows passing of 64 bit target pointers on 32 bit
+ * hosts in a single parameter
+ */
+typedef union {
+    int           host_int;
+    unsigned long host_ulong;
+    void         *host_ptr;
+    vaddr         target_ptr;
+} run_on_cpu_data;
+
+#define RUN_ON_CPU_HOST_PTR(p)    ((run_on_cpu_data){.host_ptr = (p)})
+#define RUN_ON_CPU_HOST_INT(i)    ((run_on_cpu_data){.host_int = (i)})
+#define RUN_ON_CPU_HOST_ULONG(ul) ((run_on_cpu_data){.host_ulong = (ul)})
+#define RUN_ON_CPU_TARGET_PTR(v)  ((run_on_cpu_data){.target_ptr = (v)})
+#define RUN_ON_CPU_NULL           RUN_ON_CPU_HOST_PTR(NULL)
+
+typedef void (*run_on_cpu_func)(CPUState *cpu, run_on_cpu_data data);
+
 struct qemu_work_item;
 
 /**
@@ -319,7 +337,10 @@ struct CPUState {
     MemoryRegion *memory;
 
     void *env_ptr; /* CPUArchState */
+
+    /* Writes protected by tb_lock, reads not thread-safe  */
     struct TranslationBlock *tb_jmp_cache[TB_JMP_CACHE_SIZE];
+
     struct GDBRegisterState *gdb_regs;
     int gdb_num_regs;
     int gdb_num_g_regs;
@@ -634,7 +655,7 @@ bool cpu_is_stopped(CPUState *cpu);
  *
  * Used internally in the implementation of run_on_cpu.
  */
-void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data,
+void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data,
                    QemuMutex *mutex);
 
 /**
@@ -645,7 +666,7 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data,
  *
  * Schedules the function @func for execution on the vCPU @cpu.
  */
-void run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data);
+void run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data);
 
 /**
  * async_run_on_cpu:
@@ -655,7 +676,7 @@ void run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data);
  *
  * Schedules the function @func for execution on the vCPU @cpu asynchronously.
  */
-void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data);
+void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data);
 
 /**
  * async_safe_run_on_cpu:
@@ -669,7 +690,7 @@ void async_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data);
  * Unlike run_on_cpu and async_run_on_cpu, the function is run outside the
  * BQL.
  */
-void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func, void *data);
+void async_safe_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data);
 
 /**
  * qemu_get_cpu:

kvm-all.c

@@ -1856,7 +1856,7 @@ void kvm_flush_coalesced_mmio_buffer(void)
     s->coalesced_flush_in_progress = false;
 }
 
-static void do_kvm_cpu_synchronize_state(CPUState *cpu, void *arg)
+static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
 {
     if (!cpu->kvm_vcpu_dirty) {
         kvm_arch_get_registers(cpu);
@@ -1867,11 +1867,11 @@ static void do_kvm_cpu_synchronize_state(CPUState *cpu, void *arg)
 void kvm_cpu_synchronize_state(CPUState *cpu)
 {
     if (!cpu->kvm_vcpu_dirty) {
-        run_on_cpu(cpu, do_kvm_cpu_synchronize_state, NULL);
+        run_on_cpu(cpu, do_kvm_cpu_synchronize_state, RUN_ON_CPU_NULL);
     }
 }
 
-static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, void *arg)
+static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg)
 {
     kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);
     cpu->kvm_vcpu_dirty = false;
@@ -1879,10 +1879,10 @@ static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, void *arg)
 
 void kvm_cpu_synchronize_post_reset(CPUState *cpu)
 {
-    run_on_cpu(cpu, do_kvm_cpu_synchronize_post_reset, NULL);
+    run_on_cpu(cpu, do_kvm_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
 }
 
-static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, void *arg)
+static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg)
 {
     kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE);
     cpu->kvm_vcpu_dirty = false;
@@ -1890,7 +1890,7 @@ static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, void *arg)
 
 void kvm_cpu_synchronize_post_init(CPUState *cpu)
 {
-    run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, NULL);
+    run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
 }
 
 int kvm_cpu_exec(CPUState *cpu)
@@ -2218,9 +2218,10 @@ struct kvm_set_guest_debug_data {
     int err;
 };
 
-static void kvm_invoke_set_guest_debug(CPUState *cpu, void *data)
+static void kvm_invoke_set_guest_debug(CPUState *cpu, run_on_cpu_data data)
 {
-    struct kvm_set_guest_debug_data *dbg_data = data;
+    struct kvm_set_guest_debug_data *dbg_data =
+        (struct kvm_set_guest_debug_data *) data.host_ptr;
 
     dbg_data->err = kvm_vcpu_ioctl(cpu, KVM_SET_GUEST_DEBUG,
                                    &dbg_data->dbg);
@@ -2237,7 +2238,8 @@ int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap)
     }
     kvm_arch_update_guest_debug(cpu, &data.dbg);
 
-    run_on_cpu(cpu, kvm_invoke_set_guest_debug, &data);
+    run_on_cpu(cpu, kvm_invoke_set_guest_debug,
+               RUN_ON_CPU_HOST_PTR(&data));
     return data.err;
 }
 

linux-user/elfload.c

@@ -1842,6 +1842,8 @@ static void load_elf_image(const char *image_name, int image_fd,
     info->pt_dynamic_addr = 0;
 #endif
 
+    mmap_lock();
+
     /* Find the maximum size of the image and allocate an appropriate
        amount of memory to handle that.  */
     loaddr = -1, hiaddr = 0;
@@ -2002,6 +2004,8 @@ static void load_elf_image(const char *image_name, int image_fd,
         load_symbols(ehdr, image_fd, load_bias);
     }
 
+    mmap_unlock();
+
     close(image_fd);
     return;
 

linux-user/mmap.c

@@ -41,6 +41,11 @@ void mmap_unlock(void)
     }
 }
 
+bool have_mmap_lock(void)
+{
+    return mmap_lock_count > 0 ? true : false;
+}
+
 /* Grab lock to make sure things are in a consistent state after fork().  */
 void mmap_fork_start(void)
 {

target-arm/Makefile.objs

@@ -9,4 +9,4 @@ obj-y += neon_helper.o iwmmxt_helper.o
 obj-y += gdbstub.o
 obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o helper-a64.o gdbstub64.o
 obj-y += crypto_helper.o
-obj-y += arm-powerctl.o
+obj-$(CONFIG_SOFTMMU) += arm-powerctl.o

target-arm/arm-powerctl.c

@@ -166,6 +166,8 @@ int arm_set_cpu_on(uint64_t cpuid, uint64_t entry, uint64_t context_id,
     /* Start the new CPU at the requested address */
     cpu_set_pc(target_cpu_state, entry);
 
+    qemu_cpu_kick(target_cpu_state);
+
     /* We are good to go */
     return QEMU_ARM_POWERCTL_RET_SUCCESS;
 }

target-i386/helper.c

@@ -1121,9 +1121,9 @@ typedef struct MCEInjectionParams {
     int flags;
 } MCEInjectionParams;
 
-static void do_inject_x86_mce(CPUState *cs, void *data)
+static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data)
 {
-    MCEInjectionParams *params = data;
+    MCEInjectionParams *params = data.host_ptr;
     X86CPU *cpu = X86_CPU(cs);
     CPUX86State *cenv = &cpu->env;
     uint64_t *banks = cenv->mce_banks + 4 * params->bank;
@@ -1230,7 +1230,7 @@ void cpu_x86_inject_mce(Monitor *mon, X86CPU *cpu, int bank,
         return;
     }
 
-    run_on_cpu(cs, do_inject_x86_mce, &params);
+    run_on_cpu(cs, do_inject_x86_mce, RUN_ON_CPU_HOST_PTR(&params));
     if (flags & MCE_INJECT_BROADCAST) {
         CPUState *other_cs;
 
@@ -1243,7 +1243,7 @@ void cpu_x86_inject_mce(Monitor *mon, X86CPU *cpu, int bank,
             if (other_cs == cs) {
                 continue;
             }
-            run_on_cpu(other_cs, do_inject_x86_mce, &params);
+            run_on_cpu(other_cs, do_inject_x86_mce, RUN_ON_CPU_HOST_PTR(&params));
         }
     }
 }

target-i386/kvm.c

@@ -183,7 +183,7 @@ static int kvm_get_tsc(CPUState *cs)
     return 0;
 }
 
-static inline void do_kvm_synchronize_tsc(CPUState *cpu, void *arg)
+static inline void do_kvm_synchronize_tsc(CPUState *cpu, run_on_cpu_data arg)
 {
     kvm_get_tsc(cpu);
 }
@@ -194,7 +194,7 @@ void kvm_synchronize_all_tsc(void)
 
     if (kvm_enabled()) {
         CPU_FOREACH(cpu) {
-            run_on_cpu(cpu, do_kvm_synchronize_tsc, NULL);
+            run_on_cpu(cpu, do_kvm_synchronize_tsc, RUN_ON_CPU_NULL);
         }
     }
 }

target-s390x/cpu.c

@@ -164,7 +164,7 @@ static void s390_cpu_machine_reset_cb(void *opaque)
 {
     S390CPU *cpu = opaque;
 
-    run_on_cpu(CPU(cpu), s390_do_cpu_full_reset, NULL);
+    run_on_cpu(CPU(cpu), s390_do_cpu_full_reset, RUN_ON_CPU_NULL);
 }
 #endif
 
@@ -220,7 +220,7 @@ static void s390_cpu_realizefn(DeviceState *dev, Error **errp)
     s390_cpu_gdb_init(cs);
     qemu_init_vcpu(cs);
 #if !defined(CONFIG_USER_ONLY)
-    run_on_cpu(cs, s390_do_cpu_full_reset, NULL);
+    run_on_cpu(cs, s390_do_cpu_full_reset, RUN_ON_CPU_NULL);
 #else
     cpu_reset(cs);
 #endif

target-s390x/cpu.h

@@ -502,13 +502,13 @@ static inline hwaddr decode_basedisp_s(CPUS390XState *env, uint32_t ipb,
 #define decode_basedisp_rs decode_basedisp_s
 
 /* helper functions for run_on_cpu() */
-static inline void s390_do_cpu_reset(CPUState *cs, void *arg)
+static inline void s390_do_cpu_reset(CPUState *cs, run_on_cpu_data arg)
 {
     S390CPUClass *scc = S390_CPU_GET_CLASS(cs);
 
     scc->cpu_reset(cs);
 }
-static inline void s390_do_cpu_full_reset(CPUState *cs, void *arg)
+static inline void s390_do_cpu_full_reset(CPUState *cs, run_on_cpu_data arg)
 {
     cpu_reset(cs);
 }

target-s390x/kvm.c

@@ -1607,7 +1607,7 @@ int kvm_s390_cpu_restart(S390CPU *cpu)
 {
     SigpInfo si = {};
 
-    run_on_cpu(CPU(cpu), sigp_restart, &si);
+    run_on_cpu(CPU(cpu), sigp_restart, RUN_ON_CPU_HOST_PTR(&si));
     DPRINTF("DONE: KVM cpu restart: %p\n", &cpu->env);
     return 0;
 }
@@ -1683,31 +1683,31 @@ static int handle_sigp_single_dst(S390CPU *dst_cpu, uint8_t order,
 
     switch (order) {
     case SIGP_START:
-        run_on_cpu(CPU(dst_cpu), sigp_start, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_start, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_STOP:
-        run_on_cpu(CPU(dst_cpu), sigp_stop, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_stop, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_RESTART:
-        run_on_cpu(CPU(dst_cpu), sigp_restart, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_restart, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_STOP_STORE_STATUS:
-        run_on_cpu(CPU(dst_cpu), sigp_stop_and_store_status, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_stop_and_store_status, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_STORE_STATUS_ADDR:
-        run_on_cpu(CPU(dst_cpu), sigp_store_status_at_address, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_store_status_at_address, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_STORE_ADTL_STATUS:
-        run_on_cpu(CPU(dst_cpu), sigp_store_adtl_status, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_store_adtl_status, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_SET_PREFIX:
-        run_on_cpu(CPU(dst_cpu), sigp_set_prefix, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_set_prefix, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_INITIAL_CPU_RESET:
-        run_on_cpu(CPU(dst_cpu), sigp_initial_cpu_reset, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_initial_cpu_reset, RUN_ON_CPU_HOST_PTR(&si));
         break;
     case SIGP_CPU_RESET:
-        run_on_cpu(CPU(dst_cpu), sigp_cpu_reset, &si);
+        run_on_cpu(CPU(dst_cpu), sigp_cpu_reset, RUN_ON_CPU_HOST_PTR(&si));
         break;
     default:
         DPRINTF("KVM: unknown SIGP: 0x%x\n", order);

target-s390x/misc_helper.c

@@ -126,7 +126,7 @@ static int modified_clear_reset(S390CPU *cpu)
     pause_all_vcpus();
     cpu_synchronize_all_states();
     CPU_FOREACH(t) {
-        run_on_cpu(t, s390_do_cpu_full_reset, NULL);
+        run_on_cpu(t, s390_do_cpu_full_reset, RUN_ON_CPU_NULL);
     }
     s390_cmma_reset();
     subsystem_reset();
@@ -145,7 +145,7 @@ static int load_normal_reset(S390CPU *cpu)
     pause_all_vcpus();
     cpu_synchronize_all_states();
     CPU_FOREACH(t) {
-        run_on_cpu(t, s390_do_cpu_reset, NULL);
+        run_on_cpu(t, s390_do_cpu_reset, RUN_ON_CPU_NULL);
     }
     s390_cmma_reset();
     subsystem_reset();

tcg/tcg.h

@@ -726,6 +726,7 @@ static inline bool tcg_op_buf_full(void)
 
 /* pool based memory allocation */
 
+/* tb_lock must be held for tcg_malloc_internal. */
 void *tcg_malloc_internal(TCGContext *s, int size);
 void tcg_pool_reset(TCGContext *s);
 
@@ -733,6 +734,7 @@ void tb_lock(void);
 void tb_unlock(void);
 void tb_lock_reset(void);
 
+/* Called with tb_lock held.  */
 static inline void *tcg_malloc(int size)
 {
     TCGContext *s = &tcg_ctx;

translate-all.c

@@ -31,6 +31,7 @@
 #include "tcg.h"
 #if defined(CONFIG_USER_ONLY)
 #include "qemu.h"
+#include "exec/exec-all.h"
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
 #include <sys/param.h>
 #if __FreeBSD_version >= 700104
@@ -56,16 +57,39 @@
 #include "qemu/timer.h"
 #include "exec/log.h"
 
-//#define DEBUG_TB_INVALIDATE
+/* #define DEBUG_TB_INVALIDATE */
-//#define DEBUG_FLUSH
+/* #define DEBUG_TB_FLUSH */
+/* #define DEBUG_LOCKING */
 /* make various TB consistency checks */
-//#define DEBUG_TB_CHECK
+/* #define DEBUG_TB_CHECK */
 
 #if !defined(CONFIG_USER_ONLY)
 /* TB consistency checks only implemented for usermode emulation.  */
 #undef DEBUG_TB_CHECK
 #endif
 
+/* Access to the various translations structures need to be serialised via locks
+ * for consistency. This is automatic for SoftMMU based system
+ * emulation due to its single threaded nature. In user-mode emulation
+ * access to the memory related structures are protected with the
+ * mmap_lock.
+ */
+#ifdef DEBUG_LOCKING
+#define DEBUG_MEM_LOCKS 1
+#else
+#define DEBUG_MEM_LOCKS 0
+#endif
+
+#ifdef CONFIG_SOFTMMU
+#define assert_memory_lock() do { /* nothing */ } while (0)
+#else
+#define assert_memory_lock() do {               \
+        if (DEBUG_MEM_LOCKS) {                  \
+            g_assert(have_mmap_lock());         \
+        }                                       \
+    } while (0)
+#endif
+
 #define SMC_BITMAP_USE_THRESHOLD 10
 
 typedef struct PageDesc {
@@ -173,6 +197,23 @@ void tb_lock_reset(void)
 #endif
 }
 
+#ifdef DEBUG_LOCKING
+#define DEBUG_TB_LOCKS 1
+#else
+#define DEBUG_TB_LOCKS 0
+#endif
+
+#ifdef CONFIG_SOFTMMU
+#define assert_tb_lock() do { /* nothing */ } while (0)
+#else
+#define assert_tb_lock() do {               \
+        if (DEBUG_TB_LOCKS) {               \
+            g_assert(have_tb_lock);         \
+        }                                   \
+    } while (0)
+#endif
+
+
 static TranslationBlock *tb_find_pc(uintptr_t tc_ptr);
 
 void cpu_gen_init(void)
@@ -267,7 +308,9 @@ static int encode_search(TranslationBlock *tb, uint8_t *block)
     return p - block;
 }
 
-/* The cpu state corresponding to 'searched_pc' is restored.  */
+/* The cpu state corresponding to 'searched_pc' is restored.
+ * Called with tb_lock held.
+ */
 static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
                                      uintptr_t searched_pc)
 {
@@ -320,7 +363,9 @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
 bool cpu_restore_state(CPUState *cpu, uintptr_t retaddr)
 {
     TranslationBlock *tb;
+    bool r = false;
 
+    tb_lock();
     tb = tb_find_pc(retaddr);
     if (tb) {
         cpu_restore_state_from_tb(cpu, tb, retaddr);
@@ -329,9 +374,11 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t retaddr)
             tb_phys_invalidate(tb, -1);
             tb_free(tb);
         }
-        return true;
+        r = true;
     }
-    return false;
+    tb_unlock();
+
+    return r;
 }
 
 void page_size_init(void)
@@ -421,6 +468,7 @@ static void page_init(void)
 }
 
 /* If alloc=1:
+ * Called with tb_lock held for system emulation.
  * Called with mmap_lock held for user-mode emulation.
  */
 static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
@@ -429,6 +477,10 @@ static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
     void **lp;
     int i;
 
+    if (alloc) {
+        assert_memory_lock();
+    }
+
     /* Level 1.  Always allocated.  */
     lp = l1_map + ((index >> v_l1_shift) & (v_l1_size - 1));
 
@@ -785,12 +837,18 @@ bool tcg_enabled(void)
     return tcg_ctx.code_gen_buffer != NULL;
 }
 
-/* Allocate a new translation block. Flush the translation buffer if
+/*
-   too many translation blocks or too much generated code. */
+ * Allocate a new translation block. Flush the translation buffer if
+ * too many translation blocks or too much generated code.
+ *
+ * Called with tb_lock held.
+ */
 static TranslationBlock *tb_alloc(target_ulong pc)
 {
     TranslationBlock *tb;
 
+    assert_tb_lock();
+
     if (tcg_ctx.tb_ctx.nb_tbs >= tcg_ctx.code_gen_max_blocks) {
         return NULL;
     }
@@ -801,8 +859,11 @@ static TranslationBlock *tb_alloc(target_ulong pc)
     return tb;
 }
 
+/* Called with tb_lock held.  */
 void tb_free(TranslationBlock *tb)
 {
+    assert_tb_lock();
+
     /* In practice this is mostly used for single use temporary TB
        Ignore the hard cases and just back up if this TB happens to
        be the last one generated.  */
@@ -856,20 +917,18 @@ static void page_flush_tb(void)
 }
 
 /* flush all the translation blocks */
-static void do_tb_flush(CPUState *cpu, void *data)
+static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
 {
-    unsigned tb_flush_req = (unsigned) (uintptr_t) data;
-
     tb_lock();
 
-    /* If it's already been done on request of another CPU,
+    /* If it is already been done on request of another CPU,
      * just retry.
      */
-    if (tcg_ctx.tb_ctx.tb_flush_count != tb_flush_req) {
+    if (tcg_ctx.tb_ctx.tb_flush_count != tb_flush_count.host_int) {
         goto done;
     }
 
-#if defined(DEBUG_FLUSH)
+#if defined(DEBUG_TB_FLUSH)
     printf("qemu: flush code_size=%ld nb_tbs=%d avg_tb_size=%ld\n",
            (unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer),
            tcg_ctx.tb_ctx.nb_tbs, tcg_ctx.tb_ctx.nb_tbs > 0 ?
@@ -906,8 +965,9 @@ done:
 void tb_flush(CPUState *cpu)
 {
     if (tcg_enabled()) {
-        uintptr_t tb_flush_req = atomic_mb_read(&tcg_ctx.tb_ctx.tb_flush_count);
+        unsigned tb_flush_count = atomic_mb_read(&tcg_ctx.tb_ctx.tb_flush_count);
-        async_safe_run_on_cpu(cpu, do_tb_flush, (void *) tb_flush_req);
+        async_safe_run_on_cpu(cpu, do_tb_flush,
+                              RUN_ON_CPU_HOST_INT(tb_flush_count));
     }
 }
 
@@ -925,6 +985,10 @@ do_tb_invalidate_check(struct qht *ht, void *p, uint32_t hash, void *userp)
     }
 }
 
+/* verify that all the pages have correct rights for code
+ *
+ * Called with tb_lock held.
+ */
 static void tb_invalidate_check(target_ulong address)
 {
     address &= TARGET_PAGE_MASK;
@@ -1029,7 +1093,10 @@ static inline void tb_jmp_unlink(TranslationBlock *tb)
     }
 }
 
-/* invalidate one TB */
+/* invalidate one TB
+ *
+ * Called with tb_lock held.
+ */
 void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
 {
     CPUState *cpu;
@@ -1037,6 +1104,8 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
     uint32_t h;
     tb_page_addr_t phys_pc;
 
+    assert_tb_lock();
+
     atomic_set(&tb->invalid, true);
 
     /* remove the TB from the hash list */
@@ -1117,6 +1186,8 @@ static inline void tb_alloc_page(TranslationBlock *tb,
     bool page_already_protected;
 #endif
 
+    assert_memory_lock();
+
     tb->page_addr[n] = page_addr;
     p = page_find_alloc(page_addr >> TARGET_PAGE_BITS, 1);
     tb->page_next[n] = p->first_tb;
@@ -1173,6 +1244,8 @@ static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
 {
     uint32_t h;
 
+    assert_memory_lock();
+
     /* add in the page list */
     tb_alloc_page(tb, 0, phys_pc & TARGET_PAGE_MASK);
     if (phys_page2 != -1) {
@@ -1204,6 +1277,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 #ifdef CONFIG_PROFILER
     int64_t ti;
 #endif
+    assert_memory_lock();
 
     phys_pc = get_page_addr_code(env, pc);
     if (use_icount && !(cflags & CF_IGNORE_ICOUNT)) {
@@ -1328,9 +1402,10 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
  * access: the virtual CPU will exit the current TB if code is modified inside
  * this TB.
  *
- * Called with mmap_lock held for user-mode emulation
+ * Called with mmap_lock held for user-mode emulation, grabs tb_lock
+ * Called with tb_lock held for system-mode emulation
  */
-void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
+static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_t end)
 {
     while (start < end) {
         tb_invalidate_phys_page_range(start, end, 0);
@@ -1339,6 +1414,21 @@ void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
     }
 }
 
+#ifdef CONFIG_SOFTMMU
+void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
+{
+    assert_tb_lock();
+    tb_invalidate_phys_range_1(start, end);
+}
+#else
+void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
+{
+    assert_memory_lock();
+    tb_lock();
+    tb_invalidate_phys_range_1(start, end);
+    tb_unlock();
+}
+#endif
 /*
  * Invalidate all TBs which intersect with the target physical address range
  * [start;end[. NOTE: start and end must refer to the *same* physical page.
@@ -1346,7 +1436,8 @@ void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
  * access: the virtual CPU will exit the current TB if code is modified inside
  * this TB.
  *
- * Called with mmap_lock held for user-mode emulation
+ * Called with tb_lock/mmap_lock held for user-mode emulation
+ * Called with tb_lock held for system-mode emulation
  */
 void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
                                    int is_cpu_write_access)
@@ -1368,6 +1459,9 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
     uint32_t current_flags = 0;
 #endif /* TARGET_HAS_PRECISE_SMC */
 
+    assert_memory_lock();
+    assert_tb_lock();
+
     p = page_find(start >> TARGET_PAGE_BITS);
     if (!p) {
         return;
@@ -1443,7 +1537,10 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
 }
 
 #ifdef CONFIG_SOFTMMU
-/* len must be <= 8 and start must be a multiple of len */
+/* len must be <= 8 and start must be a multiple of len.
+ * Called via softmmu_template.h when code areas are written to with
+ * tb_lock held.
+ */
 void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len)
 {
     PageDesc *p;
@@ -1457,13 +1554,17 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len)
                   (intptr_t)cpu_single_env->segs[R_CS].base);
     }
 #endif
+    assert_memory_lock();
+
     p = page_find(start >> TARGET_PAGE_BITS);
     if (!p) {
         return;
     }
     if (!p->code_bitmap &&
         ++p->code_write_count >= SMC_BITMAP_USE_THRESHOLD) {
-        /* build code bitmap */
+        /* build code bitmap.  FIXME: writes should be protected by
+         * tb_lock, reads by tb_lock or RCU.
+         */
         build_page_bitmap(p);
     }
     if (p->code_bitmap) {
@@ -1502,11 +1603,15 @@ static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
     uint32_t current_flags = 0;
 #endif
 
+    assert_memory_lock();
+
     addr &= TARGET_PAGE_MASK;
     p = page_find(addr >> TARGET_PAGE_BITS);
     if (!p) {
         return false;
     }
+
+    tb_lock();
     tb = p->first_tb;
 #ifdef TARGET_HAS_PRECISE_SMC
     if (tb && pc != 0) {
@@ -1544,9 +1649,13 @@ static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
            modifying the memory. It will ensure that it cannot modify
            itself */
         tb_gen_code(cpu, current_pc, current_cs_base, current_flags, 1);
+        /* tb_lock will be reset after cpu_loop_exit_noexc longjmps
+         * back into the cpu_exec loop. */
         return true;
     }
 #endif
+    tb_unlock();
+
     return false;
 }
 #endif
@@ -1599,11 +1708,14 @@ void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr)
         return;
     }
     ram_addr = memory_region_get_ram_addr(mr) + addr;
+    tb_lock();
     tb_invalidate_phys_page_range(ram_addr, ram_addr + 1, 0);
+    tb_unlock();
     rcu_read_unlock();
 }
 #endif /* !defined(CONFIG_USER_ONLY) */
 
+/* Called with tb_lock held.  */
 void tb_check_watchpoint(CPUState *cpu)
 {
     TranslationBlock *tb;
@@ -1640,6 +1752,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     target_ulong pc, cs_base;
     uint32_t flags;
 
+    tb_lock();
     tb = tb_find_pc(retaddr);
     if (!tb) {
         cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=%p",
@@ -1691,11 +1804,16 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     /* FIXME: In theory this could raise an exception.  In practice
        we have already translated the block once so it's probably ok.  */
     tb_gen_code(cpu, pc, cs_base, flags, cflags);
+
     /* TODO: If env->pc != tb->pc (i.e. the faulting instruction was not
-       the first in the TB) then we end up generating a whole new TB and
+     * the first in the TB) then we end up generating a whole new TB and
-       repeating the fault, which is horribly inefficient.
+     *  repeating the fault, which is horribly inefficient.
-       Better would be to execute just this insn uncached, or generate a
+     *  Better would be to execute just this insn uncached, or generate a
-       second new TB.  */
+     *  second new TB.
+     *
+     * cpu_loop_exit_noexc will longjmp back to cpu_exec where the
+     * tb_lock gets reset.
+     */
     cpu_loop_exit_noexc(cpu);
 }
 
@@ -1759,6 +1877,8 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
     TranslationBlock *tb;
     struct qht_stats hst;
 
+    tb_lock();
+
     target_code_size = 0;
     max_target_code_size = 0;
     cross_page = 0;
@@ -1820,6 +1940,8 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
             tcg_ctx.tb_ctx.tb_phys_invalidate_count);
     cpu_fprintf(f, "TLB flush count     %d\n", tlb_flush_count);
     tcg_dump_info(f, cpu_fprintf);
+
+    tb_unlock();
 }
 
 void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf)
@@ -1972,6 +2094,7 @@ void page_set_flags(target_ulong start, target_ulong end, int flags)
     assert(end < ((target_ulong)1 << L1_MAP_ADDR_SPACE_BITS));
 #endif
     assert(start < end);
+    assert_memory_lock();
 
     start = start & TARGET_PAGE_MASK;
     end = TARGET_PAGE_ALIGN(end);