6 files changed, 42 insertions, 21 deletions
diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index 536ea58..8323094 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -22,7 +22,7 @@
 #include "exec/cpu-common.h"
 #include "exec/memory.h"
 #include "qemu/thread.h"
-#include "qom/cpu.h"
+#include "hw/core/cpu.h"
 #include "qemu/rcu.h"
 
 #define EXCP_INTERRUPT 	0x10000 /* async interruption */
diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 57a9a4f..189709b 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -32,7 +32,7 @@
 #include "exec/hwaddr.h"
 #endif
 #include "exec/memattrs.h"
-#include "qom/cpu.h"
+#include "hw/core/cpu.h"
 
 #include "cpu-param.h"
 
diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h
index f7669b6..822c43c 100644
--- a/include/exec/gen-icount.h
+++ b/include/exec/gen-icount.h
@@ -7,6 +7,31 @@
 
 static TCGOp *icount_start_insn;
 
+static inline void gen_io_start(void)
+{
+    TCGv_i32 tmp = tcg_const_i32(1);
+    tcg_gen_st_i32(tmp, cpu_env,
+                   offsetof(ArchCPU, parent_obj.can_do_io) -
+                   offsetof(ArchCPU, env));
+    tcg_temp_free_i32(tmp);
+}
+
+/*
+ * cpu->can_do_io is cleared automatically at the beginning of
+ * each translation block.  The cost is minimal and only paid
+ * for -icount, plus it would be very easy to forget doing it
+ * in the translator.  Therefore, backends only need to call
+ * gen_io_start.
+ */
+static inline void gen_io_end(void)
+{
+    TCGv_i32 tmp = tcg_const_i32(0);
+    tcg_gen_st_i32(tmp, cpu_env,
+                   offsetof(ArchCPU, parent_obj.can_do_io) -
+                   offsetof(ArchCPU, env));
+    tcg_temp_free_i32(tmp);
+}
+
 static inline void gen_tb_start(TranslationBlock *tb)
 {
     TCGv_i32 count, imm;
@@ -40,6 +65,7 @@ static inline void gen_tb_start(TranslationBlock *tb)
         tcg_gen_st16_i32(count, cpu_env,
                          offsetof(ArchCPU, neg.icount_decr.u16.low) -
                          offsetof(ArchCPU, env));
+        gen_io_end();
     }
 
     tcg_temp_free_i32(count);
@@ -57,22 +83,4 @@ static inline void gen_tb_end(TranslationBlock *tb, int num_insns)
     tcg_gen_exit_tb(tb, TB_EXIT_REQUESTED);
 }
 
-static inline void gen_io_start(void)
-{
-    TCGv_i32 tmp = tcg_const_i32(1);
-    tcg_gen_st_i32(tmp, cpu_env,
-                   offsetof(ArchCPU, parent_obj.can_do_io) -
-                   offsetof(ArchCPU, env));
-    tcg_temp_free_i32(tmp);
-}
-
-static inline void gen_io_end(void)
-{
-    TCGv_i32 tmp = tcg_const_i32(0);
-    tcg_gen_st_i32(tmp, cpu_env,
-                   offsetof(ArchCPU, parent_obj.can_do_io) -
-                   offsetof(ArchCPU, env));
-    tcg_temp_free_i32(tmp);
-}
-
 #endif
diff --git a/include/exec/log.h b/include/exec/log.h
index de067f1..e2cfd43 100644
--- a/include/exec/log.h
+++ b/include/exec/log.h
@@ -2,7 +2,7 @@
 #define QEMU_EXEC_LOG_H
 
 #include "qemu/log.h"
-#include "qom/cpu.h"
+#include "hw/core/cpu.h"
 #include "disas/disas.h"
 
 /* cpu_dump_state() logging functions: */
diff --git a/include/exec/memory.h b/include/exec/memory.h
index d99eb25..fddc2ff 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -425,6 +425,7 @@ struct MemoryListener {
     void (*log_clear)(MemoryListener *listener, MemoryRegionSection *section);
     void (*log_global_start)(MemoryListener *listener);
     void (*log_global_stop)(MemoryListener *listener);
+    void (*log_global_after_sync)(MemoryListener *listener);
     void (*eventfd_add)(MemoryListener *listener, MemoryRegionSection *section,
                         bool match_data, uint64_t data, EventNotifier *e);
     void (*eventfd_del)(MemoryListener *listener, MemoryRegionSection *section,
@@ -1688,6 +1689,17 @@ MemoryRegionSection memory_region_find(MemoryRegion *mr,
 void memory_global_dirty_log_sync(void);
 
 /**
+ * memory_global_dirty_log_sync: synchronize the dirty log for all memory
+ *
+ * Synchronizes the vCPUs with a thread that is reading the dirty bitmap.
+ * This function must be called after the dirty log bitmap is cleared, and
+ * before dirty guest memory pages are read.  If you are using
+ * #DirtyBitmapSnapshot, memory_region_snapshot_and_clear_dirty() takes
+ * care of doing this.
+ */
+void memory_global_after_dirty_log_sync(void);
+
+/**
  * memory_region_transaction_begin: Start a transaction.
  *
  * During a transaction, changes will be accumulated and made visible
diff --git a/include/exec/poison.h b/include/exec/poison.h
index b862320..955eb86 100644
--- a/include/exec/poison.h
+++ b/include/exec/poison.h
@@ -35,6 +35,7 @@
 #pragma GCC poison TARGET_UNICORE32
 #pragma GCC poison TARGET_XTENSA
 
+#pragma GCC poison TARGET_ALIGNED_ONLY
 #pragma GCC poison TARGET_HAS_BFLT
 #pragma GCC poison TARGET_NAME
 #pragma GCC poison TARGET_SUPPORTS_MTTCG