4 files changed, 63 insertions, 45 deletions

diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index 4d0cb1241460..40fa780ebea7 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -175,26 +175,6 @@ void ubifs_add_bud(struct ubifs_info *c, struct ubifs_bud *bud)
 }
 
 /**
- * ubifs_create_buds_lists - create journal head buds lists for remount rw.
- * @c: UBIFS file-system description object
- */
-void ubifs_create_buds_lists(struct ubifs_info *c)
-{
-        struct rb_node *p;
-
-        spin_lock(&c->buds_lock);
-        p = rb_first(&c->buds);
-        while (p) {
-                struct ubifs_bud *bud = rb_entry(p, struct ubifs_bud, rb);
-                struct ubifs_jhead *jhead = &c->jheads[bud->jhead];
-
-                list_add_tail(&bud->list, &jhead->buds_list);
-                p = rb_next(p);
-        }
-        spin_unlock(&c->buds_lock);
-}
-
-/**
  * ubifs_add_bud_to_log - add a new bud to the log.
  * @c: UBIFS file-system description object
  * @jhead: journal head the bud belongs to
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 936f2cbfe6b6..3dbad6fbd1eb 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -317,6 +317,32 @@ int ubifs_recover_master_node(struct ubifs_info *c)
                         goto out_free;
                 }
                 memcpy(c->rcvrd_mst_node, c->mst_node, UBIFS_MST_NODE_SZ);
+
+                /*
+                 * We had to recover the master node, which means there was an
+                 * unclean reboot. However, it is possible that the master node
+                 * is clean at this point, i.e., %UBIFS_MST_DIRTY is not set.
+                 * E.g., consider the following chain of events:
+                 *
+                 * 1. UBIFS was cleanly unmounted, so the master node is clean
+                 * 2. UBIFS is being mounted R/W and starts changing the master
+                 *    node in the first (%UBIFS_MST_LNUM). A power cut happens,
+                 *    so this LEB ends up with some amount of garbage at the
+                 *    end.
+                 * 3. UBIFS is being mounted R/O. We reach this place and
+                 *    recover the master node from the second LEB
+                 *    (%UBIFS_MST_LNUM + 1). But we cannot update the media
+                 *    because we are being mounted R/O. We have to defer the
+                 *    operation.
+                 * 4. However, this master node (@c->mst_node) is marked as
+                 *    clean (since the step 1). And if we just return, the
+                 *    mount code will be confused and won't recover the master
+                 *    node when it is re-mounter R/W later.
+                 *
+                 *    Thus, to force the recovery by marking the master node as
+                 *    dirty.
+                 */
+                c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
         } else {
                 /* Write the recovered master node */
                 c->max_sqnum = le64_to_cpu(mst->ch.sqnum) - 1;
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index eed0fcff8d73..d3d6d365bfc1 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -59,6 +59,7 @@ enum {
  * @new_size: truncation new size
  * @free: amount of free space in a bud
  * @dirty: amount of dirty space in a bud from padding and deletion nodes
+ * @jhead: journal head number of the bud
  *
  * UBIFS journal replay must compare node sequence numbers, which means it must
  * build a tree of node information to insert into the TNC.
@@ -80,6 +81,7 @@ struct replay_entry {
                 struct {
                         int free;
                         int dirty;
+                        int jhead;
                 };
         };
 };
@@ -159,6 +161,11 @@ static int set_bud_lprops(struct ubifs_info *c, struct replay_entry *r)
                 err = PTR_ERR(lp);
                 goto out;
         }
+
+        /* Make sure the journal head points to the latest bud */
+        err = ubifs_wbuf_seek_nolock(&c->jheads[r->jhead].wbuf, r->lnum,
+                                     c->leb_size - r->free, UBI_SHORTTERM);
+
 out:
         ubifs_release_lprops(c);
         return err;
@@ -627,10 +634,6 @@ static int replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead,
         ubifs_assert(sleb->endpt - offs >= used);
         ubifs_assert(sleb->endpt % c->min_io_size == 0);
 
-        if (sleb->endpt + c->min_io_size <= c->leb_size && !c->ro_mount)
-                err = ubifs_wbuf_seek_nolock(&c->jheads[jhead].wbuf, lnum,
-                                             sleb->endpt, UBI_SHORTTERM);
-
         *dirty = sleb->endpt - offs - used;
         *free = c->leb_size - sleb->endpt;
 
@@ -653,12 +656,14 @@ out_dump:
  * @sqnum: sequence number
  * @free: amount of free space in bud
  * @dirty: amount of dirty space from padding and deletion nodes
+ * @jhead: journal head number for the bud
  *
  * This function inserts a reference node to the replay tree and returns zero
  * in case of success or a negative error code in case of failure.
  */
 static int insert_ref_node(struct ubifs_info *c, int lnum, int offs,
-                           unsigned long long sqnum, int free, int dirty)
+                           unsigned long long sqnum, int free, int dirty,
+                           int jhead)
 {
         struct rb_node **p = &c->replay_tree.rb_node, *parent = NULL;
         struct replay_entry *r;
@@ -688,6 +693,7 @@ static int insert_ref_node(struct ubifs_info *c, int lnum, int offs,
         r->flags = REPLAY_REF;
         r->free = free;
         r->dirty = dirty;
+        r->jhead = jhead;
 
         rb_link_node(&r->rb, parent, p);
         rb_insert_color(&r->rb, &c->replay_tree);
@@ -712,7 +718,7 @@ static int replay_buds(struct ubifs_info *c)
                 if (err)
                         return err;
                 err = insert_ref_node(c, b->bud->lnum, b->bud->start, b->sqnum,
-                                      free, dirty);
+                                      free, dirty, b->bud->jhead);
                 if (err)
                         return err;
         }
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index c75f6133206c..04ad07f4fcc3 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1257,12 +1257,12 @@ static int mount_ubifs(struct ubifs_info *c)
                 goto out_free;
         }
 
+        err = alloc_wbufs(c);
+        if (err)
+                goto out_cbuf;
+
         sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
         if (!c->ro_mount) {
-                err = alloc_wbufs(c);
-                if (err)
-                        goto out_cbuf;
-
                 /* Create background thread */
                 c->bgt = kthread_create(ubifs_bg_thread, c, "%s", c->bgt_name);
                 if (IS_ERR(c->bgt)) {
@@ -1631,12 +1631,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
         if (err)
                 goto out;
 
-        err = alloc_wbufs(c);
-        if (err)
-                goto out;
-
-        ubifs_create_buds_lists(c);
-
         /* Create background thread */
         c->bgt = kthread_create(ubifs_bg_thread, c, "%s", c->bgt_name);
         if (IS_ERR(c->bgt)) {
@@ -1671,14 +1665,25 @@ static int ubifs_remount_rw(struct ubifs_info *c)
         if (err)
                 goto out;
 
+        dbg_gen("re-mounted read-write");
+        c->remounting_rw = 0;
+
         if (c->need_recovery) {
                 c->need_recovery = 0;
                 ubifs_msg("deferred recovery completed");
+        } else {
+                /*
+                 * Do not run the debugging space check if the were doing
+                 * recovery, because when we saved the information we had the
+                 * file-system in a state where the TNC and lprops has been
+                 * modified in memory, but all the I/O operations (including a
+                 * commit) were deferred. So the file-system was in
+                 * "non-committed" state. Now the file-system is in committed
+                 * state, and of course the amount of free space will change
+                 * because, for example, the old index size was imprecise.
+                 */
+                err = dbg_check_space_info(c);
         }
-
-        dbg_gen("re-mounted read-write");
-        c->remounting_rw = 0;
-        err = dbg_check_space_info(c);
         mutex_unlock(&c->umount_mutex);
         return err;
 
@@ -1733,7 +1738,6 @@ static void ubifs_remount_ro(struct ubifs_info *c)
         if (err)
                 ubifs_ro_mode(c, err);
 
-        free_wbufs(c);
         vfree(c->orph_buf);
         c->orph_buf = NULL;
         kfree(c->write_reserve_buf);
@@ -1761,10 +1765,12 @@ static void ubifs_put_super(struct super_block *sb)
          * of the media. For example, there will be dirty inodes if we failed
          * to write them back because of I/O errors.
          */
-        ubifs_assert(atomic_long_read(&c->dirty_pg_cnt) == 0);
-        ubifs_assert(c->budg_idx_growth == 0);
-        ubifs_assert(c->budg_dd_growth == 0);
-        ubifs_assert(c->budg_data_growth == 0);
+        if (!c->ro_error) {
+                ubifs_assert(atomic_long_read(&c->dirty_pg_cnt) == 0);
+                ubifs_assert(c->budg_idx_growth == 0);
+                ubifs_assert(c->budg_dd_growth == 0);
+                ubifs_assert(c->budg_data_growth == 0);
+        }
 
         /*
          * The 'c->umount_lock' prevents races between UBIFS memory shrinker