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

Pull ext4 updates from Theodore Ts'o:
 "The one new feature added in this patch series is the ability to use
  the "punch hole" functionality for inodes that are not using extent
  maps.

  In the bug fix category, we fixed some races in the AIO and fstrim
  code, and some potential NULL pointer dereferences and memory leaks in
  error handling code paths.

  In the optimization category, we fixed a performance regression in the
  jbd2 layer introduced by commit d9b01934d56a ("jbd: fix fsync() tid
  wraparound bug", introduced in v3.0) which shows up in the AIM7
  benchmark.  We also further optimized jbd2 by minimize the amount of
  time that transaction handles are held active.

  This patch series also features some additional enhancement of the
  extent status tree, which is now used to cache extent information in a
  more efficient/compact form than what we use on-disk."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (65 commits)
  ext4: fix free clusters calculation in bigalloc filesystem
  ext4: no need to remove extent if len is 0 in ext4_es_remove_extent()
  ext4: fix xattr block allocation/release with bigalloc
  ext4: reclaim extents from extent status tree
  ext4: adjust some functions for reclaiming extents from extent status tree
  ext4: remove single extent cache
  ext4: lookup block mapping in extent status tree
  ext4: track all extent status in extent status tree
  ext4: let ext4_ext_map_blocks return EXT4_MAP_UNWRITTEN flag
  ext4: rename and improbe ext4_es_find_extent()
  ext4: add physical block and status member into extent status tree
  ext4: refine extent status tree
  ext4: use ERR_PTR() abstraction for ext4_append()
  ext4: refactor code to read directory blocks into ext4_read_dirblock()
  ext4: add debugging context for warning in ext4_da_update_reserve_space()
  ext4: use KERN_WARNING for warning messages
  jbd2: use module parameters instead of debugfs for jbd_debug
  ext4: use module parameters instead of debugfs for mballoc_debug
  ext4: start handle at the last possible moment when creating inodes
  ext4: fix the number of credits needed for acl ops with inline data
  ...

2 files changed, 285 insertions, 35 deletions

diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 7e8c36bc7082..c0457c0d1a68 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1324,6 +1324,31 @@ TRACE_EVENT(ext4_fallocate_exit,
 		  __entry->ret)
 );
 
+TRACE_EVENT(ext4_punch_hole,
+	TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
+
+	TP_ARGS(inode, offset, len),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	offset			)
+		__field(	loff_t, len			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->offset	= offset;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu offset %lld len %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->offset, __entry->len)
+);
+
 TRACE_EVENT(ext4_unlink_enter,
 	TP_PROTO(struct inode *parent, struct dentry *dentry),
 
@@ -2068,103 +2093,226 @@ TRACE_EVENT(ext4_ext_remove_space_done,
 );
 
 TRACE_EVENT(ext4_es_insert_extent,
-	TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len),
+	TP_PROTO(struct inode *inode, struct extent_status *es),
 
-	TP_ARGS(inode, start, len),
+	TP_ARGS(inode, es),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	start			)
-		__field(	loff_t, len			)
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+		__field(	ext4_lblk_t,	len		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	unsigned long long, status	)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->start	= start;
-		__entry->len	= len;
+		__entry->lblk	= es->es_lblk;
+		__entry->len	= es->es_len;
+		__entry->pblk	= ext4_es_pblock(es);
+		__entry->status	= ext4_es_status(es);
 	),
 
-	TP_printk("dev %d,%d ino %lu es [%lld/%lld)",
+	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->start, __entry->len)
+		  __entry->lblk, __entry->len,
+		  __entry->pblk, __entry->status)
 );
 
 TRACE_EVENT(ext4_es_remove_extent,
-	TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len),
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len),
 
-	TP_ARGS(inode, start, len),
+	TP_ARGS(inode, lblk, len),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field(	loff_t,	start			)
+		__field(	loff_t,	lblk			)
 		__field(	loff_t,	len			)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->start	= start;
+		__entry->lblk	= lblk;
 		__entry->len	= len;
 	),
 
 	TP_printk("dev %d,%d ino %lu es [%lld/%lld)",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->start, __entry->len)
+		  __entry->lblk, __entry->len)
 );
 
-TRACE_EVENT(ext4_es_find_extent_enter,
-	TP_PROTO(struct inode *inode, ext4_lblk_t start),
+TRACE_EVENT(ext4_es_find_delayed_extent_enter,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
 
-	TP_ARGS(inode, start),
+	TP_ARGS(inode, lblk),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	ino_t,		ino		)
-		__field(	ext4_lblk_t,	start		)
+		__field(	ext4_lblk_t,	lblk		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->start	= start;
+		__entry->lblk	= lblk;
 	),
 
-	TP_printk("dev %d,%d ino %lu start %u",
+	TP_printk("dev %d,%d ino %lu lblk %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->start)
+		  (unsigned long) __entry->ino, __entry->lblk)
 );
 
-TRACE_EVENT(ext4_es_find_extent_exit,
-	TP_PROTO(struct inode *inode, struct extent_status *es,
-		 ext4_lblk_t ret),
+TRACE_EVENT(ext4_es_find_delayed_extent_exit,
+	TP_PROTO(struct inode *inode, struct extent_status *es),
 
-	TP_ARGS(inode, es, ret),
+	TP_ARGS(inode, es),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	ino_t,		ino		)
-		__field(	ext4_lblk_t,	start		)
+		__field(	ext4_lblk_t,	lblk		)
 		__field(	ext4_lblk_t,	len		)
-		__field(	ext4_lblk_t,	ret		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	unsigned long long, status	)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->start	= es->start;
-		__entry->len	= es->len;
-		__entry->ret	= ret;
+		__entry->lblk	= es->es_lblk;
+		__entry->len	= es->es_len;
+		__entry->pblk	= ext4_es_pblock(es);
+		__entry->status	= ext4_es_status(es);
 	),
 
-	TP_printk("dev %d,%d ino %lu es [%u/%u) ret %u",
+	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->start, __entry->len, __entry->ret)
+		  __entry->lblk, __entry->len,
+		  __entry->pblk, __entry->status)
+);
+
+TRACE_EVENT(ext4_es_lookup_extent_enter,
+	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
+
+	TP_ARGS(inode, lblk),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->lblk	= lblk;
+	),
+
+	TP_printk("dev %d,%d ino %lu lblk %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->lblk)
+);
+
+TRACE_EVENT(ext4_es_lookup_extent_exit,
+	TP_PROTO(struct inode *inode, struct extent_status *es,
+		 int found),
+
+	TP_ARGS(inode, es, found),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+		__field(	ext4_lblk_t,	len		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	unsigned long long,	status	)
+		__field(	int,		found		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->lblk	= es->es_lblk;
+		__entry->len	= es->es_len;
+		__entry->pblk	= ext4_es_pblock(es);
+		__entry->status	= ext4_es_status(es);
+		__entry->found	= found;
+	),
+
+	TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->found,
+		  __entry->lblk, __entry->len,
+		  __entry->found ? __entry->pblk : 0,
+		  __entry->found ? __entry->status : 0)
+);
+
+TRACE_EVENT(ext4_es_reclaim_extents_count,
+	TP_PROTO(struct super_block *sb, int nr_cached),
+
+	TP_ARGS(sb, nr_cached),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	nr_cached		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->nr_cached	= nr_cached;
+	),
+
+	TP_printk("dev %d,%d cached objects nr %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_cached)
+);
+
+TRACE_EVENT(ext4_es_shrink_enter,
+	TP_PROTO(struct super_block *sb, int nr_to_scan),
+
+	TP_ARGS(sb, nr_to_scan),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	nr_to_scan		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->nr_to_scan	= nr_to_scan;
+	),
+
+	TP_printk("dev %d,%d nr to scan %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_to_scan)
+);
+
+TRACE_EVENT(ext4_es_shrink_exit,
+	TP_PROTO(struct super_block *sb, int shrunk_nr),
+
+	TP_ARGS(sb, shrunk_nr),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	shrunk_nr		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->shrunk_nr	= shrunk_nr;
+	),
+
+	TP_printk("dev %d,%d nr to scan %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->shrunk_nr)
 );
 
 #endif /* _TRACE_EXT4_H */
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 127993dbf322..070df49e4a1d 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -132,6 +132,104 @@ TRACE_EVENT(jbd2_submit_inode_data,
 		  (unsigned long) __entry->ino)
 );
 
+TRACE_EVENT(jbd2_handle_start,
+	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
+		 unsigned int line_no, int requested_blocks),
+
+	TP_ARGS(dev, tid, type, line_no, requested_blocks),
+
+	TP_STRUCT__entry(
+		__field(		dev_t,	dev		)
+		__field(	unsigned long,	tid		)
+		__field(	 unsigned int,	type		)
+		__field(	 unsigned int,	line_no		)
+		__field(		  int,	requested_blocks)
+	),
+
+	TP_fast_assign(
+		__entry->dev		  = dev;
+		__entry->tid		  = tid;
+		__entry->type		  = type;
+		__entry->line_no	  = line_no;
+		__entry->requested_blocks = requested_blocks;
+	),
+
+	TP_printk("dev %d,%d tid %lu type %u line_no %u "
+		  "requested_blocks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid,
+		  __entry->type, __entry->line_no, __entry->requested_blocks)
+);
+
+TRACE_EVENT(jbd2_handle_extend,
+	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
+		 unsigned int line_no, int buffer_credits,
+		 int requested_blocks),
+
+	TP_ARGS(dev, tid, type, line_no, buffer_credits, requested_blocks),
+
+	TP_STRUCT__entry(
+		__field(		dev_t,	dev		)
+		__field(	unsigned long,	tid		)
+		__field(	 unsigned int,	type		)
+		__field(	 unsigned int,	line_no		)
+		__field(		  int,	buffer_credits  )
+		__field(		  int,	requested_blocks)
+	),
+
+	TP_fast_assign(
+		__entry->dev		  = dev;
+		__entry->tid		  = tid;
+		__entry->type		  = type;
+		__entry->line_no	  = line_no;
+		__entry->buffer_credits   = buffer_credits;
+		__entry->requested_blocks = requested_blocks;
+	),
+
+	TP_printk("dev %d,%d tid %lu type %u line_no %u "
+		  "buffer_credits %d requested_blocks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid,
+		  __entry->type, __entry->line_no, __entry->buffer_credits,
+		  __entry->requested_blocks)
+);
+
+TRACE_EVENT(jbd2_handle_stats,
+	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
+		 unsigned int line_no, int interval, int sync,
+		 int requested_blocks, int dirtied_blocks),
+
+	TP_ARGS(dev, tid, type, line_no, interval, sync,
+		requested_blocks, dirtied_blocks),
+
+	TP_STRUCT__entry(
+		__field(		dev_t,	dev		)
+		__field(	unsigned long,	tid		)
+		__field(	 unsigned int,	type		)
+		__field(	 unsigned int,	line_no		)
+		__field(		  int,	interval	)
+		__field(		  int,	sync		)
+		__field(		  int,	requested_blocks)
+		__field(		  int,	dirtied_blocks	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		  = dev;
+		__entry->tid		  = tid;
+		__entry->type		  = type;
+		__entry->line_no	  = line_no;
+		__entry->interval	  = interval;
+		__entry->sync		  = sync;
+		__entry->requested_blocks = requested_blocks;
+		__entry->dirtied_blocks	  = dirtied_blocks;
+	),
+
+	TP_printk("dev %d,%d tid %lu type %u line_no %u interval %d "
+		  "sync %d requested_blocks %d dirtied_blocks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid,
+		  __entry->type, __entry->line_no, __entry->interval,
+		  __entry->sync, __entry->requested_blocks,
+		  __entry->dirtied_blocks)
+);
+
 TRACE_EVENT(jbd2_run_stats,
 	TP_PROTO(dev_t dev, unsigned long tid,
 		 struct transaction_run_stats_s *stats),
@@ -142,6 +240,7 @@ TRACE_EVENT(jbd2_run_stats,
 		__field(		dev_t,	dev		)
 		__field(	unsigned long,	tid		)
 		__field(	unsigned long,	wait		)
+		__field(	unsigned long,	request_delay	)
 		__field(	unsigned long,	running		)
 		__field(	unsigned long,	locked		)
 		__field(	unsigned long,	flushing	)
@@ -155,6 +254,7 @@ TRACE_EVENT(jbd2_run_stats,
 		__entry->dev		= dev;
 		__entry->tid		= tid;
 		__entry->wait		= stats->rs_wait;
+		__entry->request_delay	= stats->rs_request_delay;
 		__entry->running	= stats->rs_running;
 		__entry->locked		= stats->rs_locked;
 		__entry->flushing	= stats->rs_flushing;
@@ -164,10 +264,12 @@ TRACE_EVENT(jbd2_run_stats,
 		__entry->blocks_logged	= stats->rs_blocks_logged;
 	),
 
-	TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u "
-		  "logging %u handle_count %u blocks %u blocks_logged %u",
+	TP_printk("dev %d,%d tid %lu wait %u request_delay %u running %u "
+		  "locked %u flushing %u logging %u handle_count %u "
+		  "blocks %u blocks_logged %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid,
 		  jiffies_to_msecs(__entry->wait),
+		  jiffies_to_msecs(__entry->request_delay),
 		  jiffies_to_msecs(__entry->running),
 		  jiffies_to_msecs(__entry->locked),
 		  jiffies_to_msecs(__entry->flushing),