ARM host: fix generated blocks linking

This patch fixes the linking of generated blocks on an ARM host.
No need to say this brings a very nice speedup :-)

Signed-off-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

exec-all.h

@@ -211,7 +211,9 @@ static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr
 #endif
 
     /* we could use a ldr pc, [pc, #-4] kind of branch and avoid the flush */
-    *(uint32_t *)jmp_addr |= ((addr - (jmp_addr + 8)) >> 2) & 0xffffff;
+    *(uint32_t *)jmp_addr =
+        (*(uint32_t *)jmp_addr & ~0xffffff)
+        | (((addr - (jmp_addr + 8)) >> 2) & 0xffffff);
 
 #if QEMU_GNUC_PREREQ(4, 1)
     __clear_cache((char *) jmp_addr, (char *) jmp_addr + 4);