tcg: cpu-exec: remove tb_lock from the hot-path

Lock contention in the hot path of moving between existing patched
TranslationBlocks is the main drag in multithreaded performance. This
patch pushes the tb_lock() usage down to the two places that really need
it:

  - code generation (tb_gen_code)
  - jump patching (tb_add_jump)

The rest of the code doesn't really need to hold a lock as it is either
using per-CPU structures, atomically updated or designed to be used in
concurrent read situations (qht_lookup).

To keep things simple I removed the #ifdef CONFIG_USER_ONLY stuff as the
locks become NOPs anyway until the MTTCG work is completed.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Sergey Fedorov <sergey.fedorov@linaro.org>
Signed-off-by: Sergey Fedorov <sergey.fedorov@linaro.org>

Message-Id: <20160715175852.30749-10-sergey.fedorov@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

cpu-exec.c

@@ -287,35 +287,29 @@ static TranslationBlock *tb_find_slow(CPUState *cpu,
     TranslationBlock *tb;
 
     tb = tb_find_physical(cpu, pc, cs_base, flags);
-    if (tb) {
+    if (!tb) {
-        goto found;
-    }
 
-#ifdef CONFIG_USER_ONLY
+        /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
-    /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
+         * taken outside tb_lock. As system emulation is currently
-     * taken outside tb_lock.  Since we're momentarily dropping
+         * single threaded the locks are NOPs.
-     * tb_lock, there's a chance that our desired tb has been
+         */
-     * translated.
+        mmap_lock();
-     */
+        tb_lock();
-    tb_unlock();
+
-    mmap_lock();
+        /* There's a chance that our desired tb has been translated while
-    tb_lock();
+         * taking the locks so we check again inside the lock.
-    tb = tb_find_physical(cpu, pc, cs_base, flags);
+         */
-    if (tb) {
+        tb = tb_find_physical(cpu, pc, cs_base, flags);
+        if (!tb) {
+            /* if no translated code available, then translate it now */
+            tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
+        }
+
+        tb_unlock();
         mmap_unlock();
-        goto found;
     }
-#endif
 
-    /* if no translated code available, then translate it now */
+    /* We add the TB in the virtual pc hash table for the fast lookup */
-    tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
-
-#ifdef CONFIG_USER_ONLY
-    mmap_unlock();
-#endif
-
-found:
-    /* we add the TB in the virtual pc hash table */
     atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
     return tb;
 }
@@ -333,7 +327,6 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
        always be the same before a given translated block
        is executed. */
     cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-    tb_lock();
     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)) {
@@ -350,14 +343,15 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
 #endif
     /* See if we can patch the calling TB. */
     if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
+        tb_lock();
         /* Check if translation buffer has been flushed */
         if (cpu->tb_flushed) {
             cpu->tb_flushed = false;
         } else if (!tb->invalid) {
             tb_add_jump(last_tb, tb_exit, tb);
         }
+        tb_unlock();
     }
-    tb_unlock();
     return tb;
 }