On 13/02/2019 15:21, Bob Peterson wrote:
Before this patch, if gfs2_ail_empty_gl saw there was nothing on
the ail list, it would return and not flush the log. The problem
is that there could still be a revoke for the rgrp sitting on the
sd_log_le_revoke list that's been recently taken off the ail list.
But that revoke still needs to be written, and the rgrp_go_inval
still needs to call log_flush_wait to ensure the revokes are all
properly written to the journal before we relinquish control of
the glock to another node. If we give the glock to another node
before we have this knowledge, the node might crash and its journal
replayed, in which case the missing revoke would allow the journal
replay to replay the rgrp over top of the rgrp we already gave to
another node, thus overwriting its changes and corrupting the
file system.

This patch makes gfs2_ail_empty_gl still call gfs2_log_flush rather
than returning.

Signed-off-by: Bob Peterson <rpete...@redhat.com>

Yes, that looks like a good solution,


  fs/gfs2/glops.c | 23 +++++++++++++++++++++--
  fs/gfs2/log.c   |  2 +-
  fs/gfs2/log.h   |  1 +
  3 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 64b8e5e808d8..adae9ecf8311 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -94,8 +94,26 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
        tr.tr_revokes = atomic_read(&gl->gl_ail_count);
- if (!tr.tr_revokes)
-               return;
+       if (!tr.tr_revokes) {
+               /**
+                * We have nothing on the ail, but there could be revokes on
+                * the sdp revoke queue, in which case, we still want to flush
+                * the log and wait for it to finish.
+                *
+                * If the sdp revoke list is empty too, we might still have an
+                * io outstanding for writing revokes, so we should wait for
+                * it before proceeding.
+                *
+                * If none of these conditions are true, our revokes are all
+                * flushed and we can return.
+                */
+               if (!list_empty(&sdp->sd_log_le_revoke))
+                       goto flush;
+               else if (atomic_read(&sdp->sd_log_in_flight))
+                       log_flush_wait(sdp);
+               else
+                       return;
+       }
/* A shortened, inline version of gfs2_trans_begin()
           * tr->alloced is not set since the transaction structure is
@@ -110,6 +128,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
        __gfs2_ail_flush(gl, 0, tr.tr_revokes);
        gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 0d0dec3231c9..610cd2637dc5 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -515,7 +515,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned 
int new_tail)
-static void log_flush_wait(struct gfs2_sbd *sdp)
+void log_flush_wait(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 1bc9bd444b28..bd2d08d0f21c 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -75,6 +75,7 @@ extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct 
gfs2_glock *gl,
                           u32 type);
  extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
  extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control 
+extern void log_flush_wait(struct gfs2_sbd *sdp);
extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
  extern int gfs2_logd(void *data);

Reply via email to