notdirty_write: fix store-related performance problems

Every store would always cause the tb_invalidate_phys_page_fast path to be invoked,
amounting to a 40x slowdown of stores compared to loads.

Change this code to only worry about TB invalidation for regions marked as
executable (i.e. emulated executable).

Even without uc_set_native_thunks, this change fixes most of the performance
issues seen with thunking to native calls.

Signed-off-by: Andrei Warkentin <andrei.warkentin@intel.com>

qemu/include/exec/exec-all.h

@@ -464,6 +464,7 @@ tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
                                         void **hostp);
 
 void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length);
+void tlb_reset_dirty_by_vaddr(CPUState *cpu, target_ulong start1, target_ulong length);
 void tlb_set_dirty(CPUState *cpu, target_ulong vaddr);
 
 /* exec.c */

qemu/include/exec/ram_addr.h

@@ -67,12 +67,6 @@ static inline bool cpu_physical_memory_all_dirty(ram_addr_t start,
     return false;
 }
 
-static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr,
-                                                      unsigned client)
-{
-    return cpu_physical_memory_get_dirty(addr, 1, client);
-}
-
 static inline bool cpu_physical_memory_is_clean(ram_addr_t addr)
 {
     return true;