tcg: handle EXCP_ATOMIC exception for system emulation

The patch enables handling atomic code in the guest. This should be
preferably done in cpu_handle_exception(), but the current assumptions
regarding when we can execute atomic sections cause a deadlock.

The current mechanism discards the flags which were set in atomic
execution. We ensure they are properly saved by calling the
cc->cpu_exec_enter/leave() functions around the loop.

As we are running cpu_exec_step_atomic() from the outermost loop we
need to avoid an abort() when single stepping over atomic code since
debug exception longjmp will point to the the setlongjmp in
cpu_exec(). We do this by setting a new jmp_env so that it jumps back
here on an exception.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
[AJB: tweak title, merge with new patches, add mmap_lock]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
CC: Paolo Bonzini <pbonzini@redhat.com>

cpu-exec.c

@@ -228,24 +228,43 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
 
 static void cpu_exec_step(CPUState *cpu)
 {
+    CPUClass *cc = CPU_GET_CLASS(cpu);
     CPUArchState *env = (CPUArchState *)cpu->env_ptr;
     TranslationBlock *tb;
     target_ulong cs_base, pc;
     uint32_t flags;
 
     cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
+    if (sigsetjmp(cpu->jmp_env, 0) == 0) {
+        mmap_lock();
         tb_lock();
         tb = tb_gen_code(cpu, pc, cs_base, flags,
                          1 | CF_NOCACHE | CF_IGNORE_ICOUNT);
         tb->orig_tb = NULL;
         tb_unlock();
+        mmap_unlock();
+
+        cc->cpu_exec_enter(cpu);
         /* execute the generated code */
         trace_exec_tb_nocache(tb, pc);
         cpu_tb_exec(cpu, tb);
+        cc->cpu_exec_exit(cpu);
+
         tb_lock();
         tb_phys_invalidate(tb, -1);
         tb_free(tb);
         tb_unlock();
+    } else {
+        /* We may have exited due to another problem here, so we need
+         * to reset any tb_locks we may have taken but didn't release.
+         * The mmap_lock is dropped by tb_gen_code if it runs out of
+         * memory.
+         */
+#ifndef CONFIG_SOFTMMU
+        tcg_debug_assert(!have_mmap_lock());
+#endif
+        tb_lock_reset();
+    }
 }
 
 void cpu_exec_step_atomic(CPUState *cpu)

cpus.c

@@ -1348,6 +1348,11 @@ static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
                 if (r == EXCP_DEBUG) {
                     cpu_handle_guest_debug(cpu);
                     break;
+                } else if (r == EXCP_ATOMIC) {
+                    qemu_mutex_unlock_iothread();
+                    cpu_exec_step_atomic(cpu);
+                    qemu_mutex_lock_iothread();
+                    break;
                 }
             } else if (cpu->stop) {
                 if (cpu->unplug) {
@@ -1458,6 +1463,10 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
                  */
                 g_assert(cpu->halted);
                 break;
+            case EXCP_ATOMIC:
+                qemu_mutex_unlock_iothread();
+                cpu_exec_step_atomic(cpu);
+                qemu_mutex_lock_iothread();
             default:
                 /* Ignore everything else? */
                 break;