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

Pull ext4 updates from Ted Ts'o:
 "In addition to bug fixes and cleanups, there are two new features for
  ext4 in 5.14:

   - Allow applications to poll on changes to
     /sys/fs/ext4/*/errors_count

   - Add the ioctl EXT4_IOC_CHECKPOINT which allows the journal to be
     checkpointed, truncated and discarded or zero'ed"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (32 commits)
  jbd2: export jbd2_journal_[un]register_shrinker()
  ext4: notify sysfs on errors_count value change
  fs: remove bdev_try_to_free_page callback
  ext4: remove bdev_try_to_free_page() callback
  jbd2: simplify journal_clean_one_cp_list()
  jbd2,ext4: add a shrinker to release checkpointed buffers
  jbd2: remove redundant buffer io error checks
  jbd2: don't abort the journal when freeing buffers
  jbd2: ensure abort the journal if detect IO error when writing original buffer back
  jbd2: remove the out label in __jbd2_journal_remove_checkpoint()
  ext4: no need to verify new add extent block
  jbd2: clean up misleading comments for jbd2_fc_release_bufs
  ext4: add check to prevent attempting to resize an fs with sparse_super2
  ext4: consolidate checks for resize of bigalloc into ext4_resize_begin
  ext4: remove duplicate definition of ext4_xattr_ibody_inline_set()
  ext4: fsmap: fix the block/inode bitmap comment
  ext4: fix comment for s_hash_unsigned
  ext4: use local variable ei instead of EXT4_I() macro
  ext4: fix avefreec in find_group_orlov
  ext4: correct the cache_nr in tracepoint ext4_es_shrink_exit
  ...

3 files changed, 143 insertions, 2 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index fad6663cd1b0..02bf57e6f6e2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2171,7 +2171,6 @@ struct super_operations {
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 	struct dquot **(*get_dquots)(struct inode *);
 #endif
-	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 	long (*nr_cached_objects)(struct super_block *,
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index db0e1920cb12..6cc035321562 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -780,6 +780,11 @@ struct journal_s
 	unsigned long		j_flags;
 
 	/**
+	 * @j_atomic_flags: Atomic journaling state flags.
+	 */
+	unsigned long		j_atomic_flags;
+
+	/**
 	 * @j_errno:
 	 *
 	 * Is there an outstanding uncleared error on the journal (from a prior
@@ -905,6 +910,29 @@ struct journal_s
 	struct buffer_head	*j_chkpt_bhs[JBD2_NR_BATCH];
 
 	/**
+	 * @j_shrinker:
+	 *
+	 * Journal head shrinker, reclaim buffer's journal head which
+	 * has been written back.
+	 */
+	struct shrinker		j_shrinker;
+
+	/**
+	 * @j_jh_shrink_count:
+	 *
+	 * Number of journal buffers on the checkpoint list. [j_list_lock]
+	 */
+	struct percpu_counter	j_jh_shrink_count;
+
+	/**
+	 * @j_shrink_transaction:
+	 *
+	 * Record next transaction will shrink on the checkpoint list.
+	 * [j_list_lock]
+	 */
+	transaction_t		*j_shrink_transaction;
+
+	/**
 	 * @j_head:
 	 *
 	 * Journal head: identifies the first unused block in the journal.
@@ -1370,6 +1398,16 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 						 * mode */
 #define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
 #define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
+#define JBD2_JOURNAL_FLUSH_DISCARD	0x0001
+#define JBD2_JOURNAL_FLUSH_ZEROOUT	0x0002
+#define JBD2_JOURNAL_FLUSH_VALID	(JBD2_JOURNAL_FLUSH_DISCARD | \
+					JBD2_JOURNAL_FLUSH_ZEROOUT)
+
+/*
+ * Journal atomic flag definitions
+ */
+#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
+						 * buffer back to disk */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1407,6 +1445,7 @@ extern void jbd2_journal_commit_transaction(journal_t *);
 
 /* Checkpoint list management */
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy);
+unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
 void jbd2_journal_destroy_checkpoint(journal_t *journal);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
@@ -1500,7 +1539,7 @@ extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned int, unsigned int);
 extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
 extern int	 jbd2_journal_stop(handle_t *);
-extern int	 jbd2_journal_flush (journal_t *);
+extern int	 jbd2_journal_flush(journal_t *journal, unsigned int flags);
 extern void	 jbd2_journal_lock_updates (journal_t *);
 extern void	 jbd2_journal_unlock_updates (journal_t *);
 
@@ -1517,6 +1556,8 @@ extern int	   jbd2_journal_set_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern void	   jbd2_journal_clear_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
+extern int	   jbd2_journal_register_shrinker(journal_t *journal);
+extern void	   jbd2_journal_unregister_shrinker(journal_t *journal);
 extern int	   jbd2_journal_load       (journal_t *journal);
 extern int	   jbd2_journal_destroy    (journal_t *);
 extern int	   jbd2_journal_recover    (journal_t *journal);
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index d16a32867f3a..a4dfe005983d 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -394,6 +394,107 @@ TRACE_EVENT(jbd2_lock_buffer_stall,
 		__entry->stall_ms)
 );
 
+DECLARE_EVENT_CLASS(jbd2_journal_shrink,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan,
+		 unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long, nr_to_scan)
+		__field(unsigned long, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->nr_to_scan	= nr_to_scan;
+		__entry->count		= count;
+	),
+
+	TP_printk("dev %d,%d nr_to_scan %lu count %lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_to_scan, __entry->count)
+);
+
+DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_count,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count)
+);
+
+DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_scan_enter,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count)
+);
+
+TRACE_EVENT(jbd2_shrink_scan_exit,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan,
+		 unsigned long nr_shrunk, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, nr_shrunk, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long, nr_to_scan)
+		__field(unsigned long, nr_shrunk)
+		__field(unsigned long, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->nr_to_scan	= nr_to_scan;
+		__entry->nr_shrunk	= nr_shrunk;
+		__entry->count		= count;
+	),
+
+	TP_printk("dev %d,%d nr_to_scan %lu nr_shrunk %lu count %lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_to_scan, __entry->nr_shrunk,
+		  __entry->count)
+);
+
+TRACE_EVENT(jbd2_shrink_checkpoint_list,
+
+	TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid,
+		 unsigned long nr_freed, unsigned long nr_scanned,
+		 tid_t next_tid),
+
+	TP_ARGS(journal, first_tid, tid, last_tid, nr_freed,
+		nr_scanned, next_tid),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(tid_t, first_tid)
+		__field(tid_t, tid)
+		__field(tid_t, last_tid)
+		__field(unsigned long, nr_freed)
+		__field(unsigned long, nr_scanned)
+		__field(tid_t, next_tid)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->first_tid	= first_tid;
+		__entry->tid		= tid;
+		__entry->last_tid	= last_tid;
+		__entry->nr_freed	= nr_freed;
+		__entry->nr_scanned	= nr_scanned;
+		__entry->next_tid	= next_tid;
+	),
+
+	TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu "
+		  "scanned %lu next transaction %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->first_tid, __entry->tid, __entry->last_tid,
+		  __entry->nr_freed, __entry->nr_scanned, __entry->next_tid)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */