tcg: remove global exit_request

There are now only two uses of the global exit_request left.

The first ensures we exit the run_loop when we first start to process
pending work and in the kick handler. This is just as easily done by
setting the first_cpu->exit_request flag.

The second use is in the round robin kick routine. The global
exit_request ensured every vCPU would set its local exit_request and
cause a full exit of the loop. Now the iothread isn't being held while
running we can just rely on the kick handler to push us out as intended.

We lightly re-factor the main vCPU thread to ensure cpu->exit_requests
cause us to exit the main loop and process any IO requests that might
come along. As an cpu->exit_request may legitimately get squashed
while processing the EXCP_INTERRUPT exception we also check
cpu->queued_work_first to ensure queued work is expedited as soon as
possible.

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

4 files changed, 18 insertions, 26 deletions

diff --git a/cpu-exec-common.c b/cpu-exec-common.c
index e2bc053372..0504a9457b 100644
--- a/cpu-exec-common.c
+++ b/cpu-exec-common.c
@@ -23,8 +23,6 @@
 #include "exec/exec-all.h"
 #include "exec/memory-internal.h"
 
-bool exit_request;
-
 /* exit the current TB, but without causing any exception to be raised */
 void cpu_loop_exit_noexc(CPUState *cpu)
 {
diff --git a/cpu-exec.c b/cpu-exec.c
index 1bd3d72002..85f14d4194 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -568,15 +568,13 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
     *tb_exit = ret & TB_EXIT_MASK;
     switch (*tb_exit) {
     case TB_EXIT_REQUESTED:
-        /* Something asked us to stop executing
-         * chained TBs; just continue round the main
-         * loop. Whatever requested the exit will also
-         * have set something else (eg exit_request or
-         * interrupt_request) which we will handle
-         * next time around the loop.  But we need to
-         * ensure the zeroing of tcg_exit_req (see cpu_tb_exec)
-         * comes before the next read of cpu->exit_request
-         * or cpu->interrupt_request.
+        /* Something asked us to stop executing chained TBs; just
+         * continue round the main loop. Whatever requested the exit
+         * will also have set something else (eg interrupt_request)
+         * which we will handle next time around the loop.  But we
+         * need to ensure the tcg_exit_req read in generated code
+         * comes before the next read of cpu->exit_request or
+         * cpu->interrupt_request.
          */
         smp_mb();
         *last_tb = NULL;
@@ -630,10 +628,6 @@ int cpu_exec(CPUState *cpu)
 
     rcu_read_lock();
 
-    if (unlikely(atomic_mb_read(&exit_request))) {
-        cpu->exit_request = 1;
-    }
-
     cc->cpu_exec_enter(cpu);
 
     /* Calculate difference between guest clock and host clock.
diff --git a/cpus.c b/cpus.c
index 0ae8f69be5..e165d18785 100644
--- a/cpus.c
+++ b/cpus.c
@@ -793,7 +793,6 @@ static inline int64_t qemu_tcg_next_kick(void)
 static void qemu_cpu_kick_rr_cpu(void)
 {
     CPUState *cpu;
-    atomic_mb_set(&exit_request, 1);
     do {
         cpu = atomic_mb_read(&tcg_current_rr_cpu);
         if (cpu) {
@@ -1316,11 +1315,11 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
 
     start_tcg_kick_timer();
 
-    /* process any pending work */
-    atomic_mb_set(&exit_request, 1);
-
     cpu = first_cpu;
 
+    /* process any pending work */
+    cpu->exit_request = 1;
+
     while (1) {
         /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
         qemu_account_warp_timer();
@@ -1329,7 +1328,8 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
             cpu = first_cpu;
         }
 
-        for (; cpu != NULL && !exit_request; cpu = CPU_NEXT(cpu)) {
+        while (cpu && !cpu->queued_work_first && !cpu->exit_request) {
+
             atomic_mb_set(&tcg_current_rr_cpu, cpu);
 
             qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
@@ -1349,12 +1349,15 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
                 break;
             }
 
-        } /* for cpu.. */
+            cpu = CPU_NEXT(cpu);
+        } /* while (cpu && !cpu->exit_request).. */
+
         /* Does not need atomic_mb_set because a spurious wakeup is okay.  */
         atomic_set(&tcg_current_rr_cpu, NULL);
 
-        /* Pairs with smp_wmb in qemu_cpu_kick.  */
-        atomic_mb_set(&exit_request, 0);
+        if (cpu && cpu->exit_request) {
+            atomic_mb_set(&cpu->exit_request, 0);
+        }
 
         handle_icount_deadline();
 
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 4e34fc4cc1..82f0e12327 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -404,7 +404,4 @@ bool memory_region_is_unassigned(MemoryRegion *mr);
 /* vl.c */
 extern int singlestep;
 
-/* cpu-exec.c, accessed with atomic_mb_read/atomic_mb_set */
-extern bool exit_request;
-
 #endif