fix: writeback: Fix sync livelock due to b_dirty_time processing (v5.9)

See upstream commit:

  commit f9cae926f35e8230330f28c7b743ad088611a8de
  Author: Jan Kara <jack@suse.cz>
  Date:   Fri May 29 16:08:58 2020 +0200

    writeback: Fix sync livelock due to b_dirty_time processing

    When we are processing writeback for sync(2), move_expired_inodes()
    didn't set any inode expiry value (older_than_this). This can result in
    writeback never completing if there's steady stream of inodes added to
    b_dirty_time list as writeback rechecks dirty lists after each writeback
    round whether there's more work to be done. Fix the problem by using
    sync(2) start time is inode expiry value when processing b_dirty_time
    list similarly as for ordinarily dirtied inodes. This requires some
    refactoring of older_than_this handling which simplifies the code
    noticeably as a bonus.

Change-Id: I8b894b13ccc14d9b8983ee4c2810a927c319560b
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

diff --git a/include/instrumentation/events/writeback.h b/include/instrumentation/events/writeback.h
index 6a3cebc04de31fe43124c84f782f7d769e83d031..448465338225a554f58f2b214773c32aa3b58c6e 100644 (file)
--- a/include/instrumentation/events/writeback.h
+++ b/include/instrumentation/events/writeback.h
@@ -384,34 +384,48 @@ LTTNG_TRACEPOINT_EVENT_WBC_INSTANCE(wbc_balance_dirty_wait, writeback_wbc_balanc
 #endif
 LTTNG_TRACEPOINT_EVENT_WBC_INSTANCE(wbc_writepage, writeback_wbc_writepage)
 
-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,1,0))
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,9,0))
+LTTNG_TRACEPOINT_EVENT(writeback_queue_io,
+       TP_PROTO(struct bdi_writeback *wb,
+                struct wb_writeback_work *work,
+                unsigned long dirtied_before,
+                int moved),
+       TP_ARGS(wb, work, dirtied_before, moved),
+       TP_FIELDS(
+               ctf_array_text(char, name, dev_name(wb->bdi->dev), 32)
+               ctf_integer(unsigned long, older, dirtied_before)
+               ctf_integer(int, moved, moved)
+       )
+)
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0))
 LTTNG_TRACEPOINT_EVENT(writeback_queue_io,
        TP_PROTO(struct bdi_writeback *wb,
-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0))
                 struct wb_writeback_work *work,
-#else
-                unsigned long *older_than_this,
-#endif
                 int moved),
-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0))
        TP_ARGS(wb, work, moved),
-#else
+       TP_FIELDS(
+               ctf_array_text(char, name, dev_name(wb->bdi->dev), 32)
+               ctf_integer(int, moved, moved)
+       )
+)
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,1,0))
+LTTNG_TRACEPOINT_EVENT(writeback_queue_io,
+       TP_PROTO(struct bdi_writeback *wb,
+                unsigned long *older_than_this,
+                int moved),
        TP_ARGS(wb, older_than_this, moved),
-#endif
        TP_FIELDS(
                ctf_array_text(char, name, dev_name(wb->bdi->dev), 32)
-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0))
-#else
                ctf_integer(unsigned long, older,
                        older_than_this ? *older_than_this : 0)
                ctf_integer(long, age,
                        older_than_this ?
                                (jiffies - *older_than_this) * 1000 / HZ
                                : -1)
-#endif
                ctf_integer(int, moved, moved)
        )
 )
+#endif
 
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,8,0))
 LTTNG_TRACEPOINT_EVENT_MAP(global_dirty_state,
@@ -460,7 +474,7 @@ LTTNG_TRACEPOINT_EVENT_MAP(global_dirty_state,
                ctf_integer(unsigned long, dirty_limit, global_dirty_limit)
        )
 )
-#else
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,1,0))
 LTTNG_TRACEPOINT_EVENT_MAP(global_dirty_state,
 
        writeback_global_dirty_state,
@@ -485,7 +499,6 @@ LTTNG_TRACEPOINT_EVENT_MAP(global_dirty_state,
        )
 )
 #endif
-#endif
 
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0))