accel/tcg: Precompute curr_cflags into cpu->tcg_cflags

The primary motivation is to remove a dozen insns along
the fast-path in tb_lookup.  As a byproduct, this allows
us to completely remove parallel_cpus.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

3 files changed, 16 insertions, 11 deletions

diff --git a/linux-user/main.c b/linux-user/main.c
index 81f48ff54e..4f4746dce8 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -205,6 +205,7 @@ CPUArchState *cpu_copy(CPUArchState *env)
     /* Reset non arch specific state */
     cpu_reset(new_cpu);
 
+    new_cpu->tcg_cflags = cpu->tcg_cflags;
     memcpy(new_env, env, sizeof(CPUArchState));
 
     /* Clone all break/watchpoints.
diff --git a/linux-user/sh4/signal.c b/linux-user/sh4/signal.c
index cc89a48ff8..29c1ee30e6 100644
--- a/linux-user/sh4/signal.c
+++ b/linux-user/sh4/signal.c
@@ -82,9 +82,11 @@ static abi_ulong get_sigframe(struct target_sigaction *ka,
     return (sp - frame_size) & -8ul;
 }
 
-/* Notice when we're in the middle of a gUSA region and reset.
-   Note that this will only occur for !parallel_cpus, as we will
-   translate such sequences differently in a parallel context.  */
+/*
+ * Notice when we're in the middle of a gUSA region and reset.
+ * Note that this will only occur when #CF_PARALLEL is unset, as we
+ * will translate such sequences differently in a parallel context.
+ */
 static void unwind_gusa(CPUSH4State *regs)
 {
     /* If the stack pointer is sufficiently negative, and we haven't
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 389ec09764..9522f603aa 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -6481,6 +6481,16 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
         /* Grab a mutex so that thread setup appears atomic.  */
         pthread_mutex_lock(&clone_lock);
 
+        /*
+         * If this is our first additional thread, we need to ensure we
+         * generate code for parallel execution and flush old translations.
+         * Do this now so that the copy gets CF_PARALLEL too.
+         */
+        if (!(cpu->tcg_cflags & CF_PARALLEL)) {
+            cpu->tcg_cflags |= CF_PARALLEL;
+            tb_flush(cpu);
+        }
+
         /* we create a new CPU instance. */
         new_env = cpu_copy(env);
         /* Init regs that differ from the parent.  */
@@ -6521,14 +6531,6 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
         sigprocmask(SIG_BLOCK, &sigmask, &info.sigmask);
         cpu->random_seed = qemu_guest_random_seed_thread_part1();
 
-        /* If this is our first additional thread, we need to ensure we
-         * generate code for parallel execution and flush old translations.
-         */
-        if (!parallel_cpus) {
-            parallel_cpus = true;
-            tb_flush(cpu);
-        }
-
         ret = pthread_create(&info.thread, &attr, clone_func, &info);
         /* TODO: Free new CPU state if thread creation failed.  */