userspace reboot: stop post-data services and wait for them to be killed

* Refactored code around stopping services a little bit to reuse it
  between full reboot and userspace reboot.
* Add a scope_guard to fallback to full reboot in case userspace reboot
  fails.
* In case of userspace reboot init will also wait for services to be
  terminated/killed and log the ones that didn't react to
  SIGTERM/SIGKILL in time.
* If some of the services didn't react to SIGKILL, fail userspace reboot.

Test: adb reboot userspace
Bug: 135984674
Change-Id: I820c7bc406169333b0f929f0eea028d8384eb2ac

1 files changed, 30 insertions, 7 deletions

diff --git a/init/sigchld_handler.cpp b/init/sigchld_handler.cpp
index 984235de0..9b2c7d939 100644
--- a/init/sigchld_handler.cpp
+++ b/init/sigchld_handler.cpp
@@ -28,28 +28,31 @@
 #include <android-base/scopeguard.h>
 #include <android-base/stringprintf.h>
 
+#include <thread>
+
 #include "init.h"
 #include "service.h"
 #include "service_list.h"
 
-using android::base::StringPrintf;
 using android::base::boot_clock;
 using android::base::make_scope_guard;
+using android::base::StringPrintf;
+using android::base::Timer;
 
 namespace android {
 namespace init {
 
-static bool ReapOneProcess() {
+static pid_t ReapOneProcess() {
     siginfo_t siginfo = {};
     // This returns a zombie pid or informs us that there are no zombies left to be reaped.
     // It does NOT reap the pid; that is done below.
     if (TEMP_FAILURE_RETRY(waitid(P_ALL, 0, &siginfo, WEXITED | WNOHANG | WNOWAIT)) != 0) {
         PLOG(ERROR) << "waitid failed";
-        return false;
+        return 0;
     }
 
     auto pid = siginfo.si_pid;
-    if (pid == 0) return false;
+    if (pid == 0) return 0;
 
     // At this point we know we have a zombie pid, so we use this scopeguard to reap the pid
     // whenever the function returns from this point forward.
@@ -92,7 +95,7 @@ static bool ReapOneProcess() {
         LOG(INFO) << name << " received signal " << siginfo.si_status << wait_string;
     }
 
-    if (!service) return true;
+    if (!service) return pid;
 
     service->Reap(siginfo);
 
@@ -100,12 +103,32 @@ static bool ReapOneProcess() {
         ServiceList::GetInstance().RemoveService(*service);
     }
 
-    return true;
+    return pid;
 }
 
 void ReapAnyOutstandingChildren() {
-    while (ReapOneProcess()) {
+    while (ReapOneProcess() != 0) {
+    }
+}
+
+void WaitToBeReaped(const std::vector<pid_t>& pids, std::chrono::milliseconds timeout) {
+    Timer t;
+    std::vector<pid_t> alive_pids(pids.begin(), pids.end());
+    while (!alive_pids.empty() && t.duration() < timeout) {
+        pid_t pid;
+        while ((pid = ReapOneProcess()) != 0) {
+            auto it = std::find(alive_pids.begin(), alive_pids.end(), pid);
+            if (it != alive_pids.end()) {
+                alive_pids.erase(it);
+            }
+        }
+        if (alive_pids.empty()) {
+            break;
+        }
+        std::this_thread::sleep_for(50ms);
     }
+    LOG(INFO) << "Waiting for " << pids.size() << " pids to be reaped took " << t << " with "
+              << alive_pids.size() << " of them still running";
 }
 
 }  // namespace init