commit d816ab7c549438f23be5b17e888e182b2f78f03b
author Martin Liu <liumartin@google.com> Wed Sep 02 23:15:18 2020 +0800
committer Martin Liu <liumartin@google.com> Mon Sep 07 10:46:16 2020 +0800
tree 54321de845fbfc702799a1e77d7678a42443793d
parent 91bf5982820aa8b14e3a5f21c0ad5697fcd6decd

lmkd: fix possible long stall state

If the first PSI event triggers a kill, lmkd won't resume polling
immediately after the process has died. Instead, it will wait until the
next PSI event to resume the polling which is too late when the device
is under memory pressure. This happens if data communication with AMS
happens after previous polling window expired, in which case paused
handler gets reset and polling does not resume after the kill.
Fix this by changing pause handler reset logic.

Bug: 167562248
Test: memory pressure test
Signed-off-by: Martin Liu <liumartin@google.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Merged-In: I10c65c85b718a656e3d8991bf09948b96da895cb
Change-Id: I10c65c85b718a656e3d8991bf09948b96da895cb

lmkd.cpp

diff --git a/lmkd.cpp b/lmkd.cpp
index 0f46f0a..68e884e 100644
--- a/lmkd.cpp
+++ b/lmkd.cpp
@@ -3087,6 +3087,8 @@
 static void resume_polling(struct polling_params *poll_params, struct timespec curr_tm) {
     poll_params->poll_start_tm = curr_tm;
     poll_params->poll_handler = poll_params->paused_handler;
+    poll_params->polling_interval_ms = PSI_POLL_PERIOD_SHORT_MS;
+    poll_params->paused_handler = NULL;
 }
 
 static void call_handler(struct event_handler_info* handler_info,
@@ -3121,7 +3123,6 @@
         if (get_time_diff_ms(&poll_params->poll_start_tm, &curr_tm) > PSI_WINDOW_SIZE_MS) {
             /* Polled for the duration of PSI window, time to stop */
             poll_params->poll_handler = NULL;
-            poll_params->paused_handler = NULL;
         }
         break;
     }
@@ -3146,12 +3147,8 @@
             bool poll_now;
 
             clock_gettime(CLOCK_MONOTONIC_COARSE, &curr_tm);
-            if (poll_params.poll_handler == poll_params.paused_handler) {
-                /*
-                 * Just transitioned into POLLING_RESUME. Reset paused_handler
-                 * and poll immediately
-                 */
-                poll_params.paused_handler = NULL;
+            if (poll_params.update == POLLING_RESUME) {
+                /* Just transitioned into POLLING_RESUME, poll immediately. */
                 poll_now = true;
                 nevents = 0;
             } else {
@@ -3182,6 +3179,7 @@
                     stop_wait_for_proc_kill(false);
                     if (polling_paused(&poll_params)) {
                         clock_gettime(CLOCK_MONOTONIC_COARSE, &curr_tm);
+                        poll_params.update = POLLING_RESUME;
                         resume_polling(&poll_params, curr_tm);
                     }
                 }