Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (61 commits)
  ext4: Documention update for new ordered mode and delayed allocation
  ext4: do not set extents feature from the kernel
  ext4: Don't allow nonextenst mount option for large filesystem
  ext4: Enable delalloc by default.
  ext4: delayed allocation i_blocks fix for stat
  ext4: fix delalloc i_disksize early update issue
  ext4: Handle page without buffers in ext4_*_writepage()
  ext4: Add ordered mode support for delalloc
  ext4: Invert lock ordering of page_lock and transaction start in delalloc
  mm: Add range_cont mode for writeback
  ext4: delayed allocation ENOSPC handling
  percpu_counter: new function percpu_counter_sum_and_set
  ext4: Add delayed allocation support in data=writeback mode
  vfs: add hooks for ext4's delayed allocation support
  jbd2: Remove data=ordered mode support using jbd buffer heads
  ext4: Use new framework for data=ordered mode in JBD2
  jbd2: Implement data=ordered mode handling via inodes
  vfs: export filemap_fdatawrite_range()
  ext4: Fix lock inversion in ext4_ext_truncate()
  ext4: Invert the locking order of page_lock and transaction start
  ...

5 files changed, 73 insertions, 25 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index faac13e2cc5c..52e510a0aec2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1740,6 +1740,8 @@ extern int wait_on_page_writeback_range(struct address_space *mapping,
                                 pgoff_t start, pgoff_t end);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
                                 loff_t start, loff_t end, int sync_mode);
+extern int filemap_fdatawrite_range(struct address_space *mapping,
+                                loff_t start, loff_t end);
 
 extern long do_fsync(struct file *file, int datasync);
 extern void sync_supers(void);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d147f0f90360..3dd209007098 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -168,6 +168,8 @@ struct commit_header {
         unsigned char   h_chksum_size;
         unsigned char   h_padding[2];
         __be32          h_chksum[JBD2_CHECKSUM_BYTES];
+        __be64          h_commit_sec;
+        __be32          h_commit_nsec;
 };
 
 /*
@@ -379,6 +381,38 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
         bit_spin_unlock(BH_JournalHead, &bh->b_state);
 }
 
+/* Flags in jbd_inode->i_flags */
+#define __JI_COMMIT_RUNNING 0
+/* Commit of the inode data in progress. We use this flag to protect us from
+ * concurrent deletion of inode. We cannot use reference to inode for this
+ * since we cannot afford doing last iput() on behalf of kjournald
+ */
+#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+
+/**
+ * struct jbd_inode is the structure linking inodes in ordered mode
+ *   present in a transaction so that we can sync them during commit.
+ */
+struct jbd2_inode {
+        /* Which transaction does this inode belong to? Either the running
+         * transaction or the committing one. [j_list_lock] */
+        transaction_t *i_transaction;
+
+        /* Pointer to the running transaction modifying inode's data in case
+         * there is already a committing transaction touching it. [j_list_lock] */
+        transaction_t *i_next_transaction;
+
+        /* List of inodes in the i_transaction [j_list_lock] */
+        struct list_head i_list;
+
+        /* VFS inode this inode belongs to [constant during the lifetime
+         * of the structure] */
+        struct inode *i_vfs_inode;
+
+        /* Flags of inode [j_list_lock] */
+        unsigned int i_flags;
+};
+
 struct jbd2_revoke_table_s;
 
 /**
@@ -509,24 +543,12 @@ struct transaction_s
         struct journal_head     *t_reserved_list;
 
         /*
-         * Doubly-linked circular list of all buffers under writeout during
-         * commit [j_list_lock]
-         */
-        struct journal_head     *t_locked_list;
-
-        /*
          * Doubly-linked circular list of all metadata buffers owned by this
          * transaction [j_list_lock]
          */
         struct journal_head     *t_buffers;
 
         /*
-         * Doubly-linked circular list of all data buffers still to be
-         * flushed before this transaction can be committed [j_list_lock]
-         */
-        struct journal_head     *t_sync_datalist;
-
-        /*
          * Doubly-linked circular list of all forget buffers (superseded
          * buffers which we can un-checkpoint once this transaction commits)
          * [j_list_lock]
@@ -565,6 +587,12 @@ struct transaction_s
         struct journal_head     *t_log_list;
 
         /*
+         * List of inodes whose data we've modified in data=ordered mode.
+         * [j_list_lock]
+         */
+        struct list_head        t_inode_list;
+
+        /*
          * Protects info related to handles
          */
         spinlock_t              t_handle_lock;
@@ -1004,7 +1032,6 @@ extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int       jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int       jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
 extern int       jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
-extern int       jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
 extern int       jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern void      jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int       jbd2_journal_forget (handle_t *, struct buffer_head *);
@@ -1044,6 +1071,10 @@ extern void	   jbd2_journal_ack_err    (journal_t *);
 extern int         jbd2_journal_clear_err  (journal_t *);
 extern int         jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int         jbd2_journal_force_commit(journal_t *);
+extern int         jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int         jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern void        jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
+extern void        jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);
 
 /*
  * journal_head management
@@ -1179,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal)
 
 /* journaling buffer types */
 #define BJ_None         0       /* Not journaled */
-#define BJ_SyncData     1       /* Normal data: flush before commit */
-#define BJ_Metadata     2       /* Normal journaled metadata */
-#define BJ_Forget       3       /* Buffer superseded by this transaction */
-#define BJ_IO           4       /* Buffer is for temporary IO use */
-#define BJ_Shadow       5       /* Buffer contents being shadowed to the log */
-#define BJ_LogCtl       6       /* Buffer contains log descriptors */
-#define BJ_Reserved     7       /* Buffer is reserved for access by journal */
-#define BJ_Locked       8       /* Locked for I/O during commit */
-#define BJ_Types        9
+#define BJ_Metadata     1       /* Normal journaled metadata */
+#define BJ_Forget       2       /* Buffer superseded by this transaction */
+#define BJ_IO           3       /* Buffer is for temporary IO use */
+#define BJ_Shadow       4       /* Buffer contents being shadowed to the log */
+#define BJ_LogCtl       5       /* Buffer contains log descriptors */
+#define BJ_Reserved     6       /* Buffer is reserved for access by journal */
+#define BJ_Types        7
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 068a0c9946af..5c42821da2d1 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -11,11 +11,21 @@
  */
 #ifdef CONFIG_BLOCK
 
+struct mpage_data {
+        struct bio *bio;
+        sector_t last_block_in_bio;
+        get_block_t *get_block;
+        unsigned use_writepage;
+};
+
 struct writeback_control;
 
+struct bio *mpage_bio_submit(int rw, struct bio *bio);
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
                                 unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
+int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+                      void *data);
 int mpage_writepages(struct address_space *mapping,
                 struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 9007ccdfc112..208388835357 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
-s64 __percpu_counter_sum(struct percpu_counter *fbc);
+s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
-        s64 ret = __percpu_counter_sum(fbc);
+        s64 ret = __percpu_counter_sum(fbc, 0);
         return ret < 0 ? 0 : ret;
 }
 
+static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
+{
+        return __percpu_counter_sum(fbc, 1);
+}
+
+
 static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 {
-        return __percpu_counter_sum(fbc);
+        return __percpu_counter_sum(fbc, 0);
 }
 
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index bd91987c065f..12b15c561a1f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -63,6 +63,7 @@ struct writeback_control {
         unsigned for_writepages:1;      /* This is a writepages() call */
         unsigned range_cyclic:1;        /* range_start is cyclic */
         unsigned more_io:1;             /* more io to be dispatched */
+        unsigned range_cont:1;
 };
 
 /*