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> --- fs/gfs2/glops.c | 26 +++++++++++++++++++++++++- fs/gfs2/log.c | 2 +- fs/gfs2/log.h | 1 + 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index e0219b0e2229..4072f37e4278 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -92,8 +92,31 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) set_bit(TR_ATTACHED, &tr.tr_flags); /* prevent gfs2_trans_end free */ tr.tr_revokes = atomic_read(&gl->gl_ail_count); - if (!tr.tr_revokes) + 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 returning. + * + * If none of these conditions are true, our revokes are all + * flushed and we can return. + */ + gfs2_log_lock(sdp); + if (!list_empty(&sdp->sd_log_le_revoke)) { + gfs2_log_unlock(sdp); + goto flush; + } else if (atomic_read(&sdp->sd_log_in_flight)) { + gfs2_log_unlock(sdp); + log_flush_wait(sdp); + } else { + gfs2_log_unlock(sdp); + } return; + } /* A shortened, inline version of gfs2_trans_begin() * tr->alloced is not set since the transaction structure is @@ -108,6 +131,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) __gfs2_ail_flush(gl, 0, tr.tr_revokes); gfs2_trans_end(sdp); +flush: gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_AIL_EMPTY_GL); } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 11aa65dae761..6b5bac203d6d 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -536,7 +536,7 @@ 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) { DEFINE_WAIT(wait); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index 2315fca47a2b..c60f1432bb28 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -73,6 +73,7 @@ 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 *wbc); +extern void log_flush_wait(struct gfs2_sbd *sdp); extern void gfs2_log_shutdown(struct gfs2_sbd *sdp); extern int gfs2_logd(void *data); -- 2.23.0