GFS2: remove transaction glock

GFS2 has a transaction glock, which must be grabbed for every
transaction, whose purpose is to deal with freezing the filesystem.
Aside from this involving a large amount of locking, it is very easy to
make the current fsfreeze code hang on unfreezing.

This patch rewrites how gfs2 handles freezing the filesystem. The
transaction glock is removed. In it's place is a freeze glock, which is
cached (but not held) in a shared state by every node in the cluster
when the filesystem is mounted. This lock only needs to be grabbed on
freezing, and actions which need to be safe from freezing, like
recovery.

When a node wants to freeze the filesystem, it grabs this glock
exclusively.  When the freeze glock state changes on the nodes (either
from shared to unlocked, or shared to exclusive), the filesystem does a
special log flush.  gfs2_log_flush() does all the work for flushing out
the and shutting down the incore log, and then it tries to grab the
freeze glock in a shared state again.  Since the filesystem is stuck in
gfs2_log_flush, no new transaction can start, and nothing can be written
to disk. Unfreezing the filesytem simply involes dropping the freeze
glock, allowing gfs2_log_flush() to grab and then release the shared
lock, so it is cached for next time.

However, in order for the unfreezing ioctl to occur, gfs2 needs to get a
shared lock on the filesystem root directory inode to check permissions.
If that glock has already been grabbed exclusively, fsfreeze will be
unable to get the shared lock and unfreeze the filesystem.

In order to allow the unfreeze, this patch makes gfs2 grab a shared lock
on the filesystem root directory during the freeze, and hold it until it
unfreezes the filesystem.  The functions which need to grab a shared
lock in order to allow the unfreeze ioctl to be issued now use the lock
grabbed by the freeze code instead.

The freeze and unfreeze code take care to make sure that this shared
lock will not be dropped while another process is using it.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

1 files changed, 63 insertions, 30 deletions

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 4a14d504ef83..3966fadbcebd 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -301,6 +301,23 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
 }
 
 /**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+        atomic_add(blks, &sdp->sd_log_blks_free);
+        trace_gfs2_log_blocks(sdp, blks);
+        gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+                                  sdp->sd_jdesc->jd_blocks);
+        up_read(&sdp->sd_log_flush_lock);
+}
+
+/**
  * gfs2_log_reserve - Make a log reservation
  * @sdp: The GFS2 superblock
  * @blks: The number of blocks to reserve
@@ -358,7 +375,10 @@ retry:
                 wake_up(&sdp->sd_log_waitq);
 
         down_read(&sdp->sd_log_flush_lock);
-
+        if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+                gfs2_log_release(sdp, blks);
+                return -EROFS;
+        }
         return 0;
 }
 
@@ -671,7 +691,8 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
  *
  */
 
-void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+                    enum gfs2_flush_type type)
 {
         struct gfs2_trans *tr;
 
@@ -723,6 +744,42 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
         }
         spin_unlock(&sdp->sd_ail_lock);
         gfs2_log_unlock(sdp);
+
+        if (atomic_read(&sdp->sd_log_freeze))
+                type = FREEZE_FLUSH;
+        if (type != NORMAL_FLUSH) {
+                if (!sdp->sd_log_idle) {
+                        for (;;) {
+                                gfs2_ail1_start(sdp);
+                                gfs2_ail1_wait(sdp);
+                                if (gfs2_ail1_empty(sdp))
+                                        break;
+                        }
+                        atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+                        trace_gfs2_log_blocks(sdp, -1);
+                        sdp->sd_log_flush_wrapped = 0;
+                        log_write_header(sdp, 0);
+                        sdp->sd_log_head = sdp->sd_log_flush_head;
+                }
+                if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH)
+                        gfs2_log_shutdown(sdp);
+                if (type == FREEZE_FLUSH) {
+                        int error;
+
+                        atomic_set(&sdp->sd_log_freeze, 0);
+                        wake_up(&sdp->sd_log_frozen_wait);
+                        error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
+                                                   LM_ST_SHARED, 0,
+                                                   &sdp->sd_thaw_gh);
+                        if (error) {
+                                printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error);
+                                gfs2_assert_withdraw(sdp, 0);
+                        }
+                        else
+                                gfs2_glock_dq_uninit(&sdp->sd_thaw_gh);
+                }
+        }
+
         trace_gfs2_log_flush(sdp, 0);
         up_write(&sdp->sd_log_flush_lock);
 
@@ -761,7 +818,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
         if (sdp->sd_log_tr) {
                 gfs2_merge_trans(sdp->sd_log_tr, tr);
         } else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
-                gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl);
+                gfs2_assert_withdraw(sdp, tr->tr_alloced);
                 sdp->sd_log_tr = tr;
                 tr->tr_attached = 1;
         }
@@ -813,8 +870,6 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 
 void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 {
-        down_write(&sdp->sd_log_flush_lock);
-
         gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
         gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
         gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
@@ -824,38 +879,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 
         log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
 
-        gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
         gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
         gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
 
         sdp->sd_log_head = sdp->sd_log_flush_head;
         sdp->sd_log_tail = sdp->sd_log_head;
-
-        up_write(&sdp->sd_log_flush_lock);
-}
-
-
-/**
- * gfs2_meta_syncfs - sync all the buffers in a filesystem
- * @sdp: the filesystem
- *
- */
-
-void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
-{
-        gfs2_log_flush(sdp, NULL);
-        for (;;) {
-                gfs2_ail1_start(sdp);
-                gfs2_ail1_wait(sdp);
-                if (gfs2_ail1_empty(sdp))
-                        break;
-        }
-        gfs2_log_flush(sdp, NULL);
 }
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
 {
-        return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+        return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1) || atomic_read(&sdp->sd_log_freeze));
 }
 
 static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
@@ -882,14 +915,14 @@ int gfs2_logd(void *data)
 
                 if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
                         gfs2_ail1_empty(sdp);
-                        gfs2_log_flush(sdp, NULL);
+                        gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
                 }
 
                 if (gfs2_ail_flush_reqd(sdp)) {
                         gfs2_ail1_start(sdp);
                         gfs2_ail1_wait(sdp);
                         gfs2_ail1_empty(sdp);
-                        gfs2_log_flush(sdp, NULL);
+                        gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
                 }
 
                 if (!gfs2_ail_flush_reqd(sdp))