Commit e8513c01 authored by Leo Martins's avatar Leo Martins Committed by David Sterba
Browse files

btrfs: implement ref_tracker for delayed_nodes 



Add ref_tracker infrastructure for struct btrfs_delayed_node.

It is a response to the largest btrfs related crash in our fleet.  We're
seeing soft lockups in btrfs_kill_all_delayed_nodes() that seem to be a
result of delayed_nodes not being released properly.

A ref_tracker object is allocated on reference count increases and freed
on reference count decreases. The ref_tracker object stores a stack
trace of where it is allocated. The ref_tracker_dir object is embedded
in btrfs_delayed_node and keeps track of all current and some old/freed
ref_tracker objects. When a leak is detected we can print the stack
traces for all ref_trackers that have not yet been freed.

Here is a common example of taking a reference to a delayed_node and
freeing it with ref_tracker.

    struct btrfs_ref_tracker tracker;
    struct btrfs_delayed_node *node;

    node = btrfs_get_delayed_node(inode, &tracker);
    // use delayed_node...
    btrfs_release_delayed_node(node, &tracker);

There are two special cases where the delayed_node reference is "long
lived", meaning that the thread that takes the reference and the thread
that releases the reference are different. The 'inode_cache_tracker'
tracks the delayed_node stored in btrfs_inode. The 'node_list_tracker'
tracks the delayed_node stored in the btrfs_delayed_root
node_list/prepare_list. These trackers are embedded in the
btrfs_delayed_node.

btrfs_ref_tracker and btrfs_ref_tracker_dir are wrappers that either
compile to the corresponding ref_tracker structs or empty structs
depending on CONFIG_BTRFS_DEBUG. There are also btrfs wrappers for
the ref_tracker API.

Signed-off-by: default avatarLeo Martins <loemra.dev@gmail.com>
Reviewed-by: default avatarDavid Sterba <dsterba@suse.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 67e78f98

fs/btrfs/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -62,6 +62,7 @@ config BTRFS_FS_RUN_SANITY_TESTS 
config BTRFS_DEBUG

	bool "Btrfs debugging support"

	depends on BTRFS_FS

	select REF_TRACKER if STACKTRACE_SUPPORT

	help

	  Enable run-time debugging support for the btrfs filesystem.

fs/btrfs/delayed-inode.c

+120 −55

File changed.

Preview size limit exceeded, changes collapsed.

fs/btrfs/delayed-inode.h

+70 −0
Original line number Diff line number Diff line
@@ -16,6 +16,7 @@ 
#include <linux/fs.h>

#include <linux/atomic.h>

#include <linux/refcount.h>

#include <linux/ref_tracker.h>

#include "ctree.h"



struct btrfs_disk_key;
@@ -44,6 +45,22 @@ struct btrfs_delayed_root { 
	wait_queue_head_t wait;

};



struct btrfs_ref_tracker_dir {

#ifdef CONFIG_BTRFS_DEBUG

	struct ref_tracker_dir dir;

#else

	struct {} tracker;

#endif

};



struct btrfs_ref_tracker {

#ifdef CONFIG_BTRFS_DEBUG

	struct ref_tracker *tracker;

#else

	struct {} tracker;

#endif

};



#define BTRFS_DELAYED_NODE_IN_LIST	0

#define BTRFS_DELAYED_NODE_INODE_DIRTY	1

#define BTRFS_DELAYED_NODE_DEL_IREF	2
@@ -78,6 +95,12 @@ struct btrfs_delayed_node { 
	 * actual number of leaves we end up using. Protected by @mutex.

	 */

	u32 index_item_leaves;

	/* Track all references to this delayed node. */

	struct btrfs_ref_tracker_dir ref_dir;

	/* Track delayed node reference stored in node list. */

	struct btrfs_ref_tracker node_list_tracker;

	/* Track delayed node reference stored in inode cache. */

	struct btrfs_ref_tracker inode_cache_tracker;

};



struct btrfs_delayed_item {
@@ -169,4 +192,51 @@ void __cold btrfs_delayed_inode_exit(void); 
/* for debugging */

void btrfs_assert_delayed_root_empty(struct btrfs_fs_info *fs_info);



#define BTRFS_DELAYED_NODE_REF_TRACKER_QUARANTINE_COUNT		16

#define BTRFS_DELAYED_NODE_REF_TRACKER_DISPLAY_LIMIT		16



#ifdef CONFIG_BTRFS_DEBUG

static inline void btrfs_delayed_node_ref_tracker_dir_init(struct btrfs_delayed_node *node)

{

	ref_tracker_dir_init(&node->ref_dir.dir,

			     BTRFS_DELAYED_NODE_REF_TRACKER_QUARANTINE_COUNT,

			     "delayed_node");

}



static inline void btrfs_delayed_node_ref_tracker_dir_exit(struct btrfs_delayed_node *node)

{

	ref_tracker_dir_exit(&node->ref_dir.dir);

}



static inline int btrfs_delayed_node_ref_tracker_alloc(struct btrfs_delayed_node *node,

						       struct btrfs_ref_tracker *tracker,

						       gfp_t gfp)

{

	return ref_tracker_alloc(&node->ref_dir.dir, &tracker->tracker, gfp);

}



static inline int btrfs_delayed_node_ref_tracker_free(struct btrfs_delayed_node *node,

						      struct btrfs_ref_tracker *tracker)

{

	return ref_tracker_free(&node->ref_dir.dir, &tracker->tracker);

}

#else

static inline void btrfs_delayed_node_ref_tracker_dir_init(struct btrfs_delayed_node *node) { }



static inline void btrfs_delayed_node_ref_tracker_dir_exit(struct btrfs_delayed_node *node) { }



static inline int btrfs_delayed_node_ref_tracker_alloc(struct btrfs_delayed_node *node,

						       struct btrfs_ref_tracker *tracker,

						       gfp_t gfp)

{

	return 0;

}



static inline int btrfs_delayed_node_ref_tracker_free(struct btrfs_delayed_node *node,

						      struct btrfs_ref_tracker *tracker)

{

	return 0;

}

#endif



#endif