Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 bug fixes from Ted Ts'o:
 "Various bug fixes for ext4.  Perhaps the most serious bug fixed is one
  which could cause file system corruptions when performing file punch
  operations."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: avoid hang when mounting non-journal filesystems with orphan list
  ext4: lock i_mutex when truncating orphan inodes
  ext4: do not try to write superblock on ro remount w/o journal
  ext4: include journal blocks in df overhead calcs
  ext4: remove unaligned AIO warning printk
  ext4: fix an incorrect comment about i_mutex
  ext4: fix deadlock in journal_unmap_buffer()
  ext4: split off ext4_journalled_invalidatepage()
  jbd2: fix assertion failure in jbd2_journal_flush()
  ext4: check dioread_nolock on remount
  ext4: fix extent tree corruption caused by hole punch

7 files changed, 138 insertions, 56 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 26af22832a84..5ae1674ec12f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2226,13 +2226,14 @@ errout:
  * removes index from the index block.
  */
 static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
-                        struct ext4_ext_path *path)
+                        struct ext4_ext_path *path, int depth)
 {
         int err;
         ext4_fsblk_t leaf;
 
         /* free index block */
-        path--;
+        depth--;
+        path = path + depth;
         leaf = ext4_idx_pblock(path->p_idx);
         if (unlikely(path->p_hdr->eh_entries == 0)) {
                 EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
@@ -2257,6 +2258,19 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 
         ext4_free_blocks(handle, inode, NULL, leaf, 1,
                          EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+
+        while (--depth >= 0) {
+                if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr))
+                        break;
+                path--;
+                err = ext4_ext_get_access(handle, inode, path);
+                if (err)
+                        break;
+                path->p_idx->ei_block = (path+1)->p_idx->ei_block;
+                err = ext4_ext_dirty(handle, inode, path);
+                if (err)
+                        break;
+        }
         return err;
 }
 
@@ -2599,7 +2613,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
         /* if this leaf is free, then we should
          * remove it from index block above */
         if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
-                err = ext4_ext_rm_idx(handle, inode, path + depth);
+                err = ext4_ext_rm_idx(handle, inode, path, depth);
 
 out:
         return err;
@@ -2802,7 +2816,7 @@ again:
                                 /* index is empty, remove it;
                                  * handle must be already prepared by the
                                  * truncatei_leaf() */
-                                err = ext4_ext_rm_idx(handle, inode, path + i);
+                                err = ext4_ext_rm_idx(handle, inode, path, i);
                         }
                         /* root level has p_bh == NULL, brelse() eats this */
                         brelse(path[i].p_bh);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d07c27ca594a..405565a62277 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -108,14 +108,6 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 
         /* Unaligned direct AIO must be serialized; see comment above */
         if (unaligned_aio) {
-                static unsigned long unaligned_warn_time;
-
-                /* Warn about this once per day */
-                if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
-                        ext4_msg(inode->i_sb, KERN_WARNING,
-                                 "Unaligned AIO/DIO on inode %ld by %s; "
-                                 "performance will be poor.",
-                                 inode->i_ino, current->comm);
                 mutex_lock(ext4_aio_mutex(inode));
                 ext4_unwritten_wait(inode);
         }
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index dfbc1fe96674..3278e64e57b6 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -109,8 +109,6 @@ static int __sync_inode(struct inode *inode, int datasync)
  *
  * What we do is just kick off a commit and wait on it.  This will snapshot the
  * inode to disk.
- *
- * i_mutex lock is held when entering and exiting this function
  */
 
 int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cb1c1ab2720b..cbfe13bf5b2a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2880,8 +2880,6 @@ static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offs
 
 static void ext4_invalidatepage(struct page *page, unsigned long offset)
 {
-        journal_t *journal = EXT4_JOURNAL(page->mapping->host);
-
         trace_ext4_invalidatepage(page, offset);
 
         /*
@@ -2889,16 +2887,34 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset)
          */
         if (ext4_should_dioread_nolock(page->mapping->host))
                 ext4_invalidatepage_free_endio(page, offset);
+
+        /* No journalling happens on data buffers when this function is used */
+        WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
+
+        block_invalidatepage(page, offset);
+}
+
+static int __ext4_journalled_invalidatepage(struct page *page,
+                                            unsigned long offset)
+{
+        journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+        trace_ext4_journalled_invalidatepage(page, offset);
+
         /*
          * If it's a full truncate we just forget about the pending dirtying
          */
         if (offset == 0)
                 ClearPageChecked(page);
 
-        if (journal)
-                jbd2_journal_invalidatepage(journal, page, offset);
-        else
-                block_invalidatepage(page, offset);
+        return jbd2_journal_invalidatepage(journal, page, offset);
+}
+
+/* Wrapper for aops... */
+static void ext4_journalled_invalidatepage(struct page *page,
+                                           unsigned long offset)
+{
+        WARN_ON(__ext4_journalled_invalidatepage(page, offset) < 0);
 }
 
 static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -3264,7 +3280,7 @@ static const struct address_space_operations ext4_journalled_aops = {
         .write_end              = ext4_journalled_write_end,
         .set_page_dirty         = ext4_journalled_set_page_dirty,
         .bmap                   = ext4_bmap,
-        .invalidatepage         = ext4_invalidatepage,
+        .invalidatepage         = ext4_journalled_invalidatepage,
         .releasepage            = ext4_releasepage,
         .direct_IO              = ext4_direct_IO,
         .is_partially_uptodate  = block_is_partially_uptodate,
@@ -4305,6 +4321,47 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 }
 
 /*
+ * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate
+ * buffers that are attached to a page stradding i_size and are undergoing
+ * commit. In that case we have to wait for commit to finish and try again.
+ */
+static void ext4_wait_for_tail_page_commit(struct inode *inode)
+{
+        struct page *page;
+        unsigned offset;
+        journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+        tid_t commit_tid = 0;