tcg: Prepare safe tb_jmp_cache lookup out of tb_lock

Ensure atomicity of CPU's 'tb_jmp_cache' access for future translation
block lookup out of 'tb_lock'.

Note that this patch does *not* make CPU's TLB invalidation safe if it
is done from some other thread while the CPU is in its execution loop.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Sergey Fedorov <serge.fdrv@gmail.com>
Signed-off-by: Sergey Fedorov <sergey.fedorov@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20160715175852.30749-4-sergey.fedorov@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/cpu-exec.c b/cpu-exec.c
index cf511f1..32b58ed 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -315,7 +315,7 @@
 
 found:
     /* we add the TB in the virtual pc hash table */
-    cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
+    atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
     return tb;
 }
 
@@ -333,7 +333,7 @@
        is executed. */
     cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
     tb_lock();
-    tb = cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)];
+    tb = atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
     if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
                  tb->flags != flags)) {
         tb = tb_find_slow(cpu, pc, cs_base, flags);