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:
  jbd2: clean up jbd2_journal_try_to_free_buffers()
  ext4: Don't update ctime for non-extent-mapped inodes
  ext4: Fix up whitespace issues in fs/ext4/inode.c
  ext4: Fix 64-bit block type problem on 32-bit platforms
  ext4: teach the inode allocator to use a goal inode number
  ext4: Use a hash of the topdir directory name for the Orlov parent group
  ext4: document the "abort" mount option
  ext4: move the abort flag from s_mount_opts to s_mount_flags
  ext4: update the s_last_mounted field in the superblock
  ext4: change s_mount_opt to be an unsigned int
  ext4: online defrag -- Add EXT4_IOC_MOVE_EXT ioctl
  ext4: avoid unnecessary spinlock in critical POSIX ACL path
  ext3: avoid unnecessary spinlock in critical POSIX ACL path
  ext4: convert instrumentation from markers to tracepoints
  jbd2: convert instrumentation from markers to tracepoints

Documentation/ABI/testing/sysfs-fs-ext4

@@ -79,3 +79,13 @@ Description:
 		This file is read-only and shows the number of
 		kilobytes of data that have been written to this
 		filesystem since it was mounted.
+
+What:		/sys/fs/ext4/<disk>/inode_goal
+Date:		June 2008
+Contact:	"Theodore Ts'o" <tytso@mit.edu>
+Description:
+		Tuning parameter which (if non-zero) controls the goal
+		inode used by the inode allocator in p0reference to
+		all other allocation hueristics.  This is intended for
+		debugging use only, and should be 0 on production
+		systems.

Documentation/filesystems/ext4.txt

@@ -235,6 +235,10 @@ minixdf			Make 'df' act like Minix.
 
 debug			Extra debugging information is sent to syslog.
 
+abort			Simulate the effects of calling ext4_abort() for
+			debugging purposes.  This is normally used while
+			remounting a filesystem which is already mounted.
+
 errors=remount-ro	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.

fs/ext4/Makefile

@@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
 
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		ext4_jbd2.o migrate.o mballoc.o block_validity.o
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o

fs/ext4/ext4.h

@@ -352,6 +352,7 @@ struct ext4_new_group_data {
  /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
  /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
 #define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
+#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
 
 /*
  * ioctl commands in 32 bit emulation
@@ -447,6 +448,15 @@ struct ext4_inode {
 	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
 };
 
+struct move_extent {
+	__u32 reserved;		/* should be zero */
+	__u32 donor_fd;		/* donor file descriptor */
+	__u64 orig_start;	/* logical start offset in block for orig */
+	__u64 donor_start;	/* logical start offset in block for donor */
+	__u64 len;		/* block length to be moved */
+	__u64 moved_len;	/* moved block length */
+};
+#define MAX_DEFRAG_SIZE         ((1UL<<31) - 1)
 
 #define EXT4_EPOCH_BITS 2
 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
@@ -674,7 +684,6 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_ERRORS_PANIC		0x00040	/* Panic on errors */
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
-#define EXT4_MOUNT_ABORT		0x00200	/* Fatal error detected */
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
 #define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
@@ -696,17 +705,10 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
 
-/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
-#ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
 #define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
 #define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
 					 EXT4_MOUNT_##opt)
-#else
-#define EXT2_MOUNT_NOLOAD		EXT4_MOUNT_NOLOAD
-#define EXT2_MOUNT_ABORT		EXT4_MOUNT_ABORT
-#define EXT2_MOUNT_DATA_FLAGS		EXT4_MOUNT_DATA_FLAGS
-#endif
 
 #define ext4_set_bit			ext2_set_bit
 #define ext4_set_bit_atomic		ext2_set_bit_atomic
@@ -824,6 +826,13 @@ struct ext4_super_block {
 };
 
 #ifdef __KERNEL__
+
+/*
+ * run-time mount flags
+ */
+#define EXT4_MF_MNTDIR_SAMPLED	0x0001
+#define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
+
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -842,7 +851,8 @@ struct ext4_sb_info {
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
 	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
 	struct buffer_head **s_group_desc;
-	unsigned long  s_mount_opt;
+	unsigned int s_mount_opt;
+	unsigned int s_mount_flags;
 	ext4_fsblk_t s_sb_block;
 	uid_t s_resuid;
 	gid_t s_resgid;
@@ -853,6 +863,7 @@ struct ext4_sb_info {
 	int s_inode_size;
 	int s_first_ino;
 	unsigned int s_inode_readahead_blks;
+	unsigned int s_inode_goal;
 	spinlock_t s_next_gen_lock;
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
@@ -1305,7 +1316,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct
 			  dx_hash_info *hinfo);
 
 /* ialloc.c */
-extern struct inode * ext4_new_inode(handle_t *, struct inode *, int);
+extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
+				    const struct qstr *qstr, __u32 goal);
 extern void ext4_free_inode(handle_t *, struct inode *);
 extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -1329,7 +1341,7 @@ extern void ext4_discard_preallocations(struct inode *);
 extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
-		unsigned long, unsigned long, int, unsigned long *);
+		ext4_fsblk_t, unsigned long, int, unsigned long *);
 extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
@@ -1647,6 +1659,11 @@ extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
 			   struct buffer_head *bh, int flags);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
+/* move_extent.c */
+extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
+			     __u64 start_orig, __u64 start_donor,
+			     __u64 len, __u64 *moved_len);
+
 
 /*
  * Add new method to test wether block and inode bitmaps are properly

fs/ext4/ext4_extents.h

@@ -221,12 +221,16 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
 }
 
 extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
+extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
 extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
 extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 						   int num,
 						   struct ext4_ext_path *path);
+extern int ext4_can_extents_be_merged(struct inode *inode,
+				      struct ext4_extent *ex1,
+				      struct ext4_extent *ex2);
 extern int ext4_ext_try_to_merge(struct inode *inode,
 				 struct ext4_ext_path *path,
 				 struct ext4_extent *);

fs/ext4/extents.c

@@ -49,7 +49,7 @@
  * ext_pblock:
  * combine low and high parts of physical block number into ext4_fsblk_t
  */
-static ext4_fsblk_t ext_pblock(struct ext4_extent *ex)
+ext4_fsblk_t ext_pblock(struct ext4_extent *ex)
 {
 	ext4_fsblk_t block;
 
@@ -1417,7 +1417,7 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
 	return err;
 }
 
-static int
+int
 ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 				struct ext4_extent *ex2)
 {

fs/ext4/file.c

@@ -21,6 +21,8 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/mount.h>
+#include <linux/path.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -145,6 +147,38 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+static int ext4_file_open(struct inode * inode, struct file * filp)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct vfsmount *mnt = filp->f_path.mnt;
+	struct path path;
+	char buf[64], *cp;
+
+	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
+		     !(sb->s_flags & MS_RDONLY))) {
+		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+		/*
+		 * Sample where the filesystem has been mounted and
+		 * store it in the superblock for sysadmin convenience
+		 * when trying to sort through large numbers of block
+		 * devices or filesystem images.
+		 */
+		memset(buf, 0, sizeof(buf));
+		path.mnt = mnt->mnt_parent;
+		path.dentry = mnt->mnt_mountpoint;
+		path_get(&path);
+		cp = d_path(&path, buf, sizeof(buf));
+		path_put(&path);
+		if (!IS_ERR(cp)) {
+			memcpy(sbi->s_es->s_last_mounted, cp,
+			       sizeof(sbi->s_es->s_last_mounted));
+			sb->s_dirt = 1;
+		}
+	}
+	return generic_file_open(inode, filp);
+}
+
 const struct file_operations ext4_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -156,7 +190,7 @@ const struct file_operations ext4_file_operations = {
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
 	.mmap		= ext4_file_mmap,
-	.open		= generic_file_open,
+	.open		= ext4_file_open,
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
 	.splice_read	= generic_file_splice_read,

fs/ext4/fsync.c

@@ -28,10 +28,12 @@
 #include <linux/writeback.h>
 #include <linux/jbd2.h>
 #include <linux/blkdev.h>
-#include <linux/marker.h>
+
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
+#include <trace/events/ext4.h>
+
 /*
  * akpm: A new design for ext4_sync_file().
  *
@@ -52,9 +54,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
-	trace_mark(ext4_sync_file, "dev %s datasync %d ino %ld parent %ld",
+	trace_ext4_sync_file(file, dentry, datasync);
-		   inode->i_sb->s_id, datasync, inode->i_ino,
-		   dentry->d_parent->d_inode->i_ino);
 
 	/*
 	 * data=writeback:

fs/ext4/ialloc.c

@@ -23,11 +23,14 @@
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <asm/byteorder.h>
+
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
 
+#include <trace/events/ext4.h>
+
 /*
  * ialloc.c contains the inodes allocation and deallocation routines
  */
@@ -208,11 +211,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 
 	ino = inode->i_ino;
 	ext4_debug("freeing inode %lu\n", ino);
-	trace_mark(ext4_free_inode,
+	trace_ext4_free_inode(inode);
-		   "dev %s ino %lu mode %d uid %lu gid %lu bocks %llu",
-		   sb->s_id, inode->i_ino, inode->i_mode,
-		   (unsigned long) inode->i_uid, (unsigned long) inode->i_gid,
-		   (unsigned long long) inode->i_blocks);
 
 	/*
 	 * Note: we must free any quota before locking the superblock,
@@ -471,7 +470,8 @@ void get_orlov_stats(struct super_block *sb, ext4_group_t g,
  */
 
 static int find_group_orlov(struct super_block *sb, struct inode *parent,
-			    ext4_group_t *group, int mode)
+			    ext4_group_t *group, int mode,
+			    const struct qstr *qstr)
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -486,6 +486,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	struct ext4_group_desc *desc;
 	struct orlov_stats stats;
 	int flex_size = ext4_flex_bg_size(sbi);
+	struct dx_hash_info hinfo;
 
 	ngroups = real_ngroups;
 	if (flex_size > 1) {
@@ -507,7 +508,13 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		int best_ndir = inodes_per_group;
 		int ret = -1;
 
-		get_random_bytes(&grp, sizeof(grp));
+		if (qstr) {
+			hinfo.hash_version = DX_HASH_HALF_MD4;
+			hinfo.seed = sbi->s_hash_seed;
+			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
+			grp = hinfo.hash;
+		} else
+			get_random_bytes(&grp, sizeof(grp));
 		parent_group = (unsigned)grp % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			g = (parent_group + i) % ngroups;
@@ -650,7 +657,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		*group = parent_group + flex_size;
 		if (*group > ngroups)
 			*group = 0;
-		return find_group_orlov(sb, parent, group, mode);
+		return find_group_orlov(sb, parent, group, mode, 0);
 	}
 
 	/*
@@ -791,7 +798,8 @@ err_ret:
  * For other inodes, search forward from the parent directory's block
  * group to find a free inode.
  */
-struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
+struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
+			     const struct qstr *qstr, __u32 goal)
 {
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
@@ -815,14 +823,23 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 
 	sb = dir->i_sb;
 	ngroups = ext4_get_groups_count(sb);
-	trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
+	trace_ext4_request_inode(dir, mode);
-		   dir->i_ino, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	ei = EXT4_I(inode);
 	sbi = EXT4_SB(sb);
 
+	if (!goal)
+		goal = sbi->s_inode_goal;
+
+	if (goal && goal < le32_to_cpu(sbi->s_es->s_inodes_count)) {
+		group = (goal - 1) / EXT4_INODES_PER_GROUP(sb);
+		ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb);
+		ret2 = 0;
+		goto got_group;
+	}
+
 	if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
 		ret2 = find_group_flex(sb, dir, &group);
 		if (ret2 == -1) {
@@ -841,7 +858,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 		if (test_opt(sb, OLDALLOC))
 			ret2 = find_group_dir(sb, dir, &group);
 		else
-			ret2 = find_group_orlov(sb, dir, &group, mode);
+			ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
 	} else
 		ret2 = find_group_other(sb, dir, &group, mode);
 
@@ -851,7 +868,7 @@ got_group:
 	if (ret2 == -1)
 		goto out;
 
-	for (i = 0; i < ngroups; i++) {
+	for (i = 0; i < ngroups; i++, ino = 0) {
 		err = -EIO;
 
 		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
@@ -863,8 +880,6 @@ got_group:
 		if (!inode_bitmap_bh)
 			goto fail;
 
-		ino = 0;
-
 repeat_in_this_group:
 		ino = ext4_find_next_zero_bit((unsigned long *)
 					      inode_bitmap_bh->b_data,
@@ -1047,8 +1062,7 @@ got:
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
-	trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d",
+	trace_ext4_allocate_inode(inode, dir, mode);
-		   sb->s_id, inode->i_ino, dir->i_ino, mode);
 	goto really_out;
 fail:
 	ext4_std_error(sb, err);

fs/ext4/inode.c

@@ -37,11 +37,14 @@
 #include <linux/namei.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
 #include "ext4_extents.h"
 
+#include <trace/events/ext4.h>
+
 #define MPAGE_DA_EXTENT_TAIL 0x01
 
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
@@ -78,7 +81,7 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
  * If the handle isn't valid we're not journaling so there's nothing to do.
  */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
-			struct buffer_head *bh, ext4_fsblk_t blocknr)
+		struct buffer_head *bh, ext4_fsblk_t blocknr)
 {
 	int err;
 
@@ -90,7 +93,7 @@ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 	BUFFER_TRACE(bh, "enter");
 
 	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
-		  "data mode %lx\n",
+		  "data mode %x\n",
 		  bh, is_metadata, inode->i_mode,
 		  test_opt(inode->i_sb, DATA_FLAGS));
 
@@ -329,8 +332,8 @@ static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
  */
 
 static int ext4_block_to_path(struct inode *inode,
-			ext4_lblk_t i_block,
+			      ext4_lblk_t i_block,
-			ext4_lblk_t offsets[4], int *boundary)
+			      ext4_lblk_t offsets[4], int *boundary)
 {
 	int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
 	int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
@@ -362,9 +365,9 @@ static int ext4_block_to_path(struct inode *inode,
 		final = ptrs;
 	} else {
 		ext4_warning(inode->i_sb, "ext4_block_to_path",
-				"block %lu > max in inode %lu",
+			     "block %lu > max in inode %lu",
-				i_block + direct_blocks +
+			     i_block + direct_blocks +
-				indirect_blocks + double_blocks, inode->i_ino);
+			     indirect_blocks + double_blocks, inode->i_ino);
 	}
 	if (boundary)
 		*boundary = final - 1 - (i_block & (ptrs - 1));
@@ -379,25 +382,25 @@ static int __ext4_check_blockref(const char *function, struct inode *inode,
 
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
-		if (blk && 
+		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), 
+		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
 						    blk, 1))) {
 			ext4_error(inode->i_sb, function,
 				   "invalid block reference %u "
 				   "in inode #%lu", blk, inode->i_ino);
- 			return -EIO;
+			return -EIO;
- 		}
+		}
- 	}
+	}
- 	return 0;
+	return 0;
 }
 
 
 #define ext4_check_indirect_blockref(inode, bh)                         \
-        __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data,  \
+	__ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data,  \
 			      EXT4_ADDR_PER_BLOCK((inode)->i_sb))
 
 #define ext4_check_inode_blockref(inode)                                \
-        __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data,   \
+	__ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data,   \
 			      EXT4_NDIR_BLOCKS)
 
 /**
@@ -447,7 +450,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 		bh = sb_getblk(sb, le32_to_cpu(p->key));
 		if (unlikely(!bh))
 			goto failure;
-                  
+
 		if (!bh_uptodate_or_lock(bh)) {
 			if (bh_submit_read(bh) < 0) {
 				put_bh(bh);
@@ -459,7 +462,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 				goto failure;
 			}
 		}
-		
+
 		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
 		/* Reader: end */
 		if (!p->key)
@@ -552,7 +555,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
  *	returns it.
  */
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
-		Indirect *partial)
+				   Indirect *partial)
 {
 	/*
 	 * XXX need to get goal block from mballoc's data structures
@@ -574,7 +577,7 @@ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
  *	direct and indirect blocks.
  */
 static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
-		int blocks_to_boundary)
+				 int blocks_to_boundary)
 {
 	unsigned int count = 0;
 
@@ -610,9 +613,9 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
  *		direct blocks
  */
 static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, ext4_fsblk_t goal,
+			     ext4_lblk_t iblock, ext4_fsblk_t goal,
-				int indirect_blks, int blks,
+			     int indirect_blks, int blks,
-				ext4_fsblk_t new_blocks[4], int *err)
+			     ext4_fsblk_t new_blocks[4], int *err)
 {
 	struct ext4_allocation_request ar;
 	int target, i;
@@ -683,10 +686,10 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	}
 	if (!*err) {
 		if (target == blks) {
-		/*
+			/*
-		 * save the new block number
+			 * save the new block number
-		 * for the first direct block
+			 * for the first direct block
-		 */
+			 */
 			new_blocks[index] = current_block;
 		}
 		blk_allocated += ar.len;
@@ -728,9 +731,9 @@ failed_out:
  *	as described above and return 0.
  */
 static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, int indirect_blks,
+			     ext4_lblk_t iblock, int indirect_blks,
-				int *blks, ext4_fsblk_t goal,
+			     int *blks, ext4_fsblk_t goal,
-				ext4_lblk_t *offsets, Indirect *branch)
+			     ext4_lblk_t *offsets, Indirect *branch)
 {
 	int blocksize = inode->i_sb->s_blocksize;
 	int i, n = 0;
@@ -777,7 +780,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 			 * the chain to point to the new allocated
 			 * data blocks numbers
 			 */
-			for (i=1; i < num; i++)
+			for (i = 1; i < num; i++)
 				*(branch[n].p + i) = cpu_to_le32(++current_block);
 		}
 		BUFFER_TRACE(bh, "marking uptodate");
@@ -820,7 +823,8 @@ failed:
  * chain to new block and return 0.
  */
 static int ext4_splice_branch(handle_t *handle, struct inode *inode,
-			ext4_lblk_t block, Indirect *where, int num, int blks)
+			      ext4_lblk_t block, Indirect *where, int num,
+			      int blks)
 {
 	int i;
 	int err = 0;
@@ -852,10 +856,6 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	}
 
 	/* We are done with atomic stuff, now do the rest of housekeeping */
-
-	inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-
 	/* had we spliced it onto indirect block? */
 	if (where->bh) {
 		/*
@@ -874,8 +874,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	} else {
 		/*
 		 * OK, we spliced it into the inode itself on a direct block.
-		 * Inode was dirtied above.
 		 */
+		ext4_mark_inode_dirty(handle, inode);
 		jbd_debug(5, "splicing direct\n");
 	}
 	return err;
@@ -921,9 +921,9 @@ err_out:
  * blocks.
  */
 static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
-				  ext4_lblk_t iblock, unsigned int maxblocks,
+			       ext4_lblk_t iblock, unsigned int maxblocks,
-				  struct buffer_head *bh_result,
+			       struct buffer_head *bh_result,
-				  int flags)
+			       int flags)
 {
 	int err = -EIO;
 	ext4_lblk_t offsets[4];
@@ -939,7 +939,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
 	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
 	depth = ext4_block_to_path(inode, iblock, offsets,
-					&blocks_to_boundary);
+				   &blocks_to_boundary);
 
 	if (depth == 0)
 		goto out;
@@ -987,8 +987,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	 * Block out ext4_truncate while we alter the tree
 	 */
 	err = ext4_alloc_branch(handle, inode, iblock, indirect_blks,
-					&count, goal,
+				&count, goal,
-					offsets + (partial - chain), partial);
+				offsets + (partial - chain), partial);
 
 	/*
 	 * The ext4_splice_branch call will free and forget any buffers
@@ -999,8 +999,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	 */
 	if (!err)
 		err = ext4_splice_branch(handle, inode, iblock,
-					partial, indirect_blks, count);
+					 partial, indirect_blks, count);
-	else 
+	else
 		goto cleanup;
 
 	set_buffer_new(bh_result);
@@ -1172,7 +1172,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 	up_read((&EXT4_I(inode)->i_data_sem));
 
 	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, block, 
+		int ret = check_block_validity(inode, block,
 					       bh->b_blocknr, retval);
 		if (ret != 0)
 			return ret;
@@ -1254,7 +1254,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, block, 
+		int ret = check_block_validity(inode, block,
 					       bh->b_blocknr, retval);
 		if (ret != 0)
 			return ret;
@@ -1405,8 +1405,7 @@ static int walk_page_buffers(handle_t *handle,
 
 	for (bh = head, block_start = 0;
 	     ret == 0 && (bh != head || !block_start);
-	     block_start = block_end, bh = next)
+	     block_start = block_end, bh = next) {
-	{
 		next = bh->b_this_page;
 		block_end = block_start + blocksize;
 		if (block_end <= from || block_start >= to) {
@@ -1447,7 +1446,7 @@ static int walk_page_buffers(handle_t *handle,
  * write.
  */
 static int do_journal_get_write_access(handle_t *handle,
-					struct buffer_head *bh)
+				       struct buffer_head *bh)
 {
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
@@ -1455,27 +1454,24 @@ static int do_journal_get_write_access(handle_t *handle,
 }
 
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+			    loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
+			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret, needed_blocks;
 	handle_t *handle;
 	int retries = 0;
 	struct page *page;
- 	pgoff_t index;
+	pgoff_t index;
 	unsigned from, to;
 
-	trace_mark(ext4_write_begin,
+	trace_ext4_write_begin(inode, pos, len, flags);
-		   "dev %s ino %lu pos %llu len %u flags %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
 	 * we allocate blocks but write fails for some reason
 	 */
 	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
- 	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
@@ -1523,7 +1519,7 @@ retry:
 		ext4_journal_stop(handle);
 		if (pos + len > inode->i_size) {
 			vmtruncate(inode, inode->i_size);
-			/* 
+			/*
 			 * If vmtruncate failed early the inode might
 			 * still be on the orphan list; we need to
 			 * make sure the inode is removed from the
@@ -1550,9 +1546,9 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 }
 
 static int ext4_generic_write_end(struct file *file,
-				struct address_space *mapping,
+				  struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
+				  loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				  struct page *page, void *fsdata)
 {
 	int i_size_changed = 0;
 	struct inode *inode = mapping->host;
@@ -1603,18 +1599,15 @@ static int ext4_generic_write_end(struct file *file,
  * buffers are managed internally.
  */
 static int ext4_ordered_write_end(struct file *file,
-				struct address_space *mapping,
+				  struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
+				  loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				  struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 
-	trace_mark(ext4_ordered_write_end,
+	trace_ext4_ordered_write_end(inode, pos, len, copied);
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
 	ret = ext4_jbd2_file_inode(handle, inode);
 
 	if (ret == 0) {
@@ -1636,7 +1629,7 @@ static int ext4_ordered_write_end(struct file *file,
 
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1650,18 +1643,15 @@ static int ext4_ordered_write_end(struct file *file,
 }
 
 static int ext4_writeback_write_end(struct file *file,
-				struct address_space *mapping,
+				    struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
+				    loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				    struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 
-	trace_mark(ext4_writeback_write_end,
+	trace_ext4_writeback_write_end(inode, pos, len, copied);
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
 	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
@@ -1681,7 +1671,7 @@ static int ext4_writeback_write_end(struct file *file,
 
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1694,9 +1684,9 @@ static int ext4_writeback_write_end(struct file *file,
 }
 
 static int ext4_journalled_write_end(struct file *file,
-				struct address_space *mapping,
+				     struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
+				     loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				     struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
@@ -1705,10 +1695,7 @@ static int ext4_journalled_write_end(struct file *file,
 	unsigned from, to;
 	loff_t new_i_size;
 
-	trace_mark(ext4_journalled_write_end,
+	trace_ext4_journalled_write_end(inode, pos, len, copied);
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
@@ -1747,7 +1734,7 @@ static int ext4_journalled_write_end(struct file *file,
 		ret = ret2;
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1854,7 +1841,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 }
 
 static void ext4_da_page_release_reservation(struct page *page,
-						unsigned long offset)
+					     unsigned long offset)
 {
 	int to_release = 0;
 	struct buffer_head *head, *bh;
@@ -2554,9 +2541,7 @@ static int ext4_da_writepage(struct page *page,
 	struct buffer_head *page_bufs;
 	struct inode *inode = page->mapping->host;
 
-	trace_mark(ext4_da_writepage,
+	trace_ext4_da_writepage(inode, page);
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2667,19 +2652,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
-	trace_mark(ext4_da_writepages,
+	trace_ext4_da_writepages(inode, wbc);
-		   "dev %s ino %lu nr_t_write %ld "
-		   "pages_skipped %ld range_start %llu "
-		   "range_end %llu nonblocking %d "
-		   "for_kupdate %d for_reclaim %d "
-		   "for_writepages %d range_cyclic %d",
-		   inode->i_sb->s_id, inode->i_ino,
-		   wbc->nr_to_write, wbc->pages_skipped,
-		   (unsigned long long) wbc->range_start,
-		   (unsigned long long) wbc->range_end,
-		   wbc->nonblocking, wbc->for_kupdate,
-		   wbc->for_reclaim, wbc->for_writepages,
-		   wbc->range_cyclic);
 
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
@@ -2693,13 +2666,13 @@ static int ext4_da_writepages(struct address_space *mapping,
 	 * If the filesystem has aborted, it is read-only, so return
 	 * right away instead of dumping stack traces later on that
 	 * will obscure the real source of the problem.  We test
-	 * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+	 * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
 	 * the latter could be true if the filesystem is mounted
 	 * read-only, and in that case, ext4_da_writepages should
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
 		return -EROFS;
 
 	/*
@@ -2845,14 +2818,7 @@ out_writepages:
 	if (!no_nrwrite_index_update)
 		wbc->no_nrwrite_index_update = 0;
 	wbc->nr_to_write -= nr_to_writebump;
-	trace_mark(ext4_da_writepage_result,
+	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
-		   "dev %s ino %lu ret %d pages_written %d "
-		   "pages_skipped %ld congestion %d "
-		   "more_io %d no_nrwrite_index_update %d",
-		   inode->i_sb->s_id, inode->i_ino, ret,
-		   pages_written, wbc->pages_skipped,
-		   wbc->encountered_congestion, wbc->more_io,
-		   wbc->no_nrwrite_index_update);
 	return ret;
 }
 
@@ -2884,8 +2850,8 @@ static int ext4_nonda_switch(struct super_block *sb)
 }
 
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+			       loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
+			       struct page **pagep, void **fsdata)
 {
 	int ret, retries = 0;
 	struct page *page;
@@ -2904,11 +2870,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 					len, flags, pagep, fsdata);
 	}
 	*fsdata = (void *)0;
-
+	trace_ext4_da_write_begin(inode, pos, len, flags);
-	trace_mark(ext4_da_write_begin,
-		   "dev %s ino %lu pos %llu len %u flags %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, flags);
 retry:
 	/*
 	 * With delayed allocation, we don't log the i_disksize update
@@ -2959,7 +2921,7 @@ out:
  * when write to the end of file but not require block allocation
  */
 static int ext4_da_should_update_i_disksize(struct page *page,
-					 unsigned long offset)
+					    unsigned long offset)
 {
 	struct buffer_head *bh;
 	struct inode *inode = page->mapping->host;
@@ -2978,9 +2940,9 @@ static int ext4_da_should_update_i_disksize(struct page *page,
 }
 
 static int ext4_da_write_end(struct file *file,
-				struct address_space *mapping,
+			     struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
+			     loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+			     struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
@@ -3001,10 +2963,7 @@ static int ext4_da_write_end(struct file *file,
 		}
 	}
 
-	trace_mark(ext4_da_write_end,
+	trace_ext4_da_write_end(inode, pos, len, copied);
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
 	start = pos & (PAGE_CACHE_SIZE - 1);
 	end = start + copied - 1;
 
@@ -3081,7 +3040,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
 	 * not strictly speaking necessary (and for users of
 	 * laptop_mode, not even desirable).  However, to do otherwise
 	 * would require replicating code paths in:
-	 * 
+	 *
 	 * ext4_da_writepages() ->
 	 *    write_cache_pages() ---> (via passed in callback function)
 	 *        __mpage_da_writepage() -->
@@ -3101,7 +3060,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
 	 * write out the pages, but rather only collect contiguous
 	 * logical block extents, call the multi-block allocator, and
 	 * then update the buffer heads with the block allocations.
-	 * 
+	 *
 	 * For now, though, we'll cheat by calling filemap_flush(),
 	 * which will map the blocks, and start the I/O, but not
 	 * actually wait for the I/O to complete.
@@ -3237,7 +3196,7 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
  *
  */
 static int __ext4_normal_writepage(struct page *page,
-				struct writeback_control *wbc)
+				   struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 
@@ -3249,15 +3208,13 @@ static int __ext4_normal_writepage(struct page *page,
 }
 
 static int ext4_normal_writepage(struct page *page,
-				struct writeback_control *wbc)
+				 struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
-	trace_mark(ext4_normal_writepage,
+	trace_ext4_normal_writepage(inode, page);
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -3287,7 +3244,7 @@ static int ext4_normal_writepage(struct page *page,
 }
 
 static int __ext4_journalled_writepage(struct page *page,
-				struct writeback_control *wbc)
+				       struct writeback_control *wbc)
 {
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
@@ -3337,15 +3294,13 @@ out:
 }
 
 static int ext4_journalled_writepage(struct page *page,
-				struct writeback_control *wbc)
+				     struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
-	trace_mark(ext4_journalled_writepage,
+	trace_ext4_journalled_writepage(inode, page);
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -3442,8 +3397,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
  * VFS code falls back into buffered path in that case so we are safe.
  */
 static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
-			const struct iovec *iov, loff_t offset,
+			      const struct iovec *iov, loff_t offset,
-			unsigned long nr_segs)
+			      unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -3763,7 +3718,8 @@ static inline int all_zeroes(__le32 *p, __le32 *q)
  *			(no partially truncated stuff there).  */
 
 static Indirect *ext4_find_shared(struct inode *inode, int depth,
-			ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top)
+				  ext4_lblk_t offsets[4], Indirect chain[4],
+				  __le32 *top)
 {
 	Indirect *partial, *p;
 	int k, err;
@@ -3819,8 +3775,10 @@ no_top:
  * than `count' because there can be holes in there.
  */
 static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
-		struct buffer_head *bh, ext4_fsblk_t block_to_free,
+			      struct buffer_head *bh,
-		unsigned long count, __le32 *first, __le32 *last)
+			      ext4_fsblk_t block_to_free,
+			      unsigned long count, __le32 *first,
+			      __le32 *last)
 {
 	__le32 *p;
 	if (try_to_extend_transaction(handle, inode)) {
@@ -3837,10 +3795,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	}
 
 	/*
-	 * Any buffers which are on the journal will be in memory. We find
+	 * Any buffers which are on the journal will be in memory. We
-	 * them on the hash table so jbd2_journal_revoke() will run jbd2_journal_forget()
+	 * find them on the hash table so jbd2_journal_revoke() will
-	 * on them.  We've already detached each block from the file, so
+	 * run jbd2_journal_forget() on them.  We've already detached
-	 * bforget() in jbd2_journal_forget() should be safe.
+	 * each block from the file, so bforget() in
+	 * jbd2_journal_forget() should be safe.
 	 *
 	 * AKPM: turn on bforget in jbd2_journal_forget()!!!
 	 */
@@ -4212,7 +4171,7 @@ void ext4_truncate(struct inode *inode)
 				   (__le32*)partial->bh->b_data+addr_per_block,
 				   (chain+n-1) - partial);
 		BUFFER_TRACE(partial->bh, "call brelse");
-		brelse (partial->bh);
+		brelse(partial->bh);
 		partial--;
 	}
 do_indirects:
@@ -4453,8 +4412,9 @@ void ext4_get_inode_flags(struct ext4_inode_info *ei)
 	if (flags & S_DIRSYNC)
 		ei->i_flags |= EXT4_DIRSYNC_FL;
 }
+
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
-					struct ext4_inode_info *ei)
+				  struct ext4_inode_info *ei)
 {
 	blkcnt_t i_blocks ;
 	struct inode *inode = &(ei->vfs_inode);
@@ -4569,7 +4529,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 					EXT4_GOOD_OLD_INODE_SIZE +
 					ei->i_extra_isize;
 			if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
-				 ei->i_state |= EXT4_STATE_XATTR;
+				ei->i_state |= EXT4_STATE_XATTR;
 		}
 	} else
 		ei->i_extra_isize = 0;
@@ -4588,7 +4548,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    ((ei->i_file_acl < 
+	    ((ei->i_file_acl <
 	      (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
 	       EXT4_SB(sb)->s_gdb_count)) ||
 	     (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
@@ -4603,15 +4563,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		     !ext4_inode_is_fast_symlink(inode)))
 			/* Validate extent which is part of inode */
 			ret = ext4_ext_check_inode(inode);
- 	} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		   (S_ISLNK(inode->i_mode) &&
 		    !ext4_inode_is_fast_symlink(inode))) {
-	 	/* Validate block references which are part of inode */
+		/* Validate block references which are part of inode */
 		ret = ext4_check_inode_blockref(inode);
 	}
 	if (ret) {
- 		brelse(bh);
+		brelse(bh);
- 		goto bad_inode;
+		goto bad_inode;
 	}
 
 	if (S_ISREG(inode->i_mode)) {
@@ -4642,7 +4602,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	} else {
 		brelse(bh);
 		ret = -EIO;
-		ext4_error(inode->i_sb, __func__, 
+		ext4_error(inode->i_sb, __func__,
 			   "bogus i_mode (%o) for inode=%lu",
 			   inode->i_mode, inode->i_ino);
 		goto bad_inode;
@@ -4795,8 +4755,9 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le32(new_encode_dev(inode->i_rdev));
 			raw_inode->i_block[2] = 0;
 		}
-	} else for (block = 0; block < EXT4_N_BLOCKS; block++)
+	} else
-		raw_inode->i_block[block] = ei->i_data[block];
+		for (block = 0; block < EXT4_N_BLOCKS; block++)
+			raw_inode->i_block[block] = ei->i_data[block];
 
 	raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
 	if (ei->i_extra_isize) {
@@ -5150,7 +5111,7 @@ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
  * Give this, we know that the caller already has write access to iloc->bh.
  */
 int ext4_mark_iloc_dirty(handle_t *handle,
-		struct inode *inode, struct ext4_iloc *iloc)
+			 struct inode *inode, struct ext4_iloc *iloc)
 {
 	int err = 0;
 

fs/ext4/ioctl.c

@@ -14,6 +14,7 @@
 #include <linux/compat.h>
 #include <linux/smp_lock.h>
 #include <linux/mount.h>
+#include <linux/file.h>
 #include <asm/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -213,6 +214,41 @@ setversion_out:
 
 		return err;
 	}
+
+	case EXT4_IOC_MOVE_EXT: {
+		struct move_extent me;
+		struct file *donor_filp;
+		int err;
+
+		if (copy_from_user(&me,
+			(struct move_extent __user *)arg, sizeof(me)))
+			return -EFAULT;
+
+		donor_filp = fget(me.donor_fd);
+		if (!donor_filp)
+			return -EBADF;
+
+		if (!capable(CAP_DAC_OVERRIDE)) {
+			if ((current->real_cred->fsuid != inode->i_uid) ||
+				!(inode->i_mode & S_IRUSR) ||
+				!(donor_filp->f_dentry->d_inode->i_mode &
+				S_IRUSR)) {
+				fput(donor_filp);
+				return -EACCES;
+			}
+		}
+
+		err = ext4_move_extents(filp, donor_filp, me.orig_start,
+					me.donor_start, me.len, &me.moved_len);
+		fput(donor_filp);
+
+		if (!err)
+			if (copy_to_user((struct move_extent *)arg,
+				&me, sizeof(me)))
+				return -EFAULT;
+		return err;
+	}
+
 	case EXT4_IOC_GROUP_ADD: {
 		struct ext4_new_group_data input;
 		struct super_block *sb = inode->i_sb;

fs/ext4/mballoc.c

@@ -22,6 +22,8 @@
  */
 
 #include "mballoc.h"
+#include <trace/events/ext4.h>
+
 /*
  * MUSTDO:
  *   - test ext4_ext_search_left() and ext4_ext_search_right()
@@ -340,8 +342,6 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 						ext4_group_t group);
 static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
 
-
-
 static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
 {
 #if BITS_PER_LONG == 64
@@ -2859,9 +2859,8 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 		discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
 			+ entry->start_blk
 			+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
-		trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u",
+		trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
-			   sb->s_id, (unsigned long long) discard_block,
+					  entry->count);
-			   entry->count);
 		sb_issue_discard(sb, discard_block, entry->count);
 
 		kmem_cache_free(ext4_free_ext_cachep, entry);
@@ -3629,10 +3628,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 
 	mb_debug("new inode pa %p: %llu/%u for %u\n", pa,
 			pa->pa_pstart, pa->pa_len, pa->pa_lstart);
-	trace_mark(ext4_mb_new_inode_pa,
+	trace_ext4_mb_new_inode_pa(ac, pa);
-		   "dev %s ino %lu pstart %llu len %u lstart %u",
-		   sb->s_id, ac->ac_inode->i_ino,
-		   pa->pa_pstart, pa->pa_len, pa->pa_lstart);
 
 	ext4_mb_use_inode_pa(ac, pa);
 	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
@@ -3691,9 +3687,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 	pa->pa_type = MB_GROUP_PA;
 
 	mb_debug("new group pa %p: %llu/%u for %u\n", pa,
-		 pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+			pa->pa_pstart, pa->pa_len, pa->pa_lstart);
-	trace_mark(ext4_mb_new_group_pa, "dev %s pstart %llu len %u lstart %u",
+	trace_ext4_mb_new_group_pa(ac, pa);
-		   sb->s_id, pa->pa_pstart, pa->pa_len, pa->pa_lstart);
 
 	ext4_mb_use_group_pa(ac, pa);
 	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
@@ -3783,10 +3778,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			ext4_mb_store_history(ac);
 		}
 
-		trace_mark(ext4_mb_release_inode_pa,
+		trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit,
-			   "dev %s ino %lu block %llu count %u",
+					       next - bit);
-			   sb->s_id, pa->pa_inode->i_ino, grp_blk_start + bit,
-			   next - bit);
 		mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
 		bit = next + 1;
 	}
@@ -3820,8 +3813,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	if (ac)
 		ac->ac_op = EXT4_MB_HISTORY_DISCARD;
 
-	trace_mark(ext4_mb_release_group_pa, "dev %s pstart %llu len %d",
+	trace_ext4_mb_release_group_pa(ac, pa);
-		   sb->s_id, pa->pa_pstart, pa->pa_len);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
 	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
@@ -3889,6 +3881,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 
 	INIT_LIST_HEAD(&list);
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+	if (ac)
+		ac->ac_sb = sb;
 repeat:
 	ext4_lock_group(sb, group);
 	list_for_each_entry_safe(pa, tmp,
@@ -3987,12 +3981,15 @@ void ext4_discard_preallocations(struct inode *inode)
 	}
 
 	mb_debug("discard preallocation for inode %lu\n", inode->i_ino);
-	trace_mark(ext4_discard_preallocations, "dev %s ino %lu", sb->s_id,
+	trace_ext4_discard_preallocations(inode);
-		   inode->i_ino);
 
 	INIT_LIST_HEAD(&list);
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+	if (ac) {
+		ac->ac_sb = sb;
+		ac->ac_inode = inode;
+	}
 repeat:
 	/* first, collect all pa's in the inode */
 	spin_lock(&ei->i_prealloc_lock);
@@ -4276,6 +4273,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 
 	INIT_LIST_HEAD(&discard_list);
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+	if (ac)
+		ac->ac_sb = sb;
 
 	spin_lock(&lg->lg_prealloc_lock);
 	list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order],
@@ -4445,8 +4444,7 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
 	int ret;
 	int freed = 0;
 
-	trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d",
+	trace_ext4_mb_discard_preallocations(sb, needed);
-		   sb->s_id, needed);
 	for (i = 0; i < ngroups && needed > 0; i++) {
 		ret = ext4_mb_discard_group_preallocations(sb, i, needed);
 		freed += ret;
@@ -4475,17 +4473,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	sb = ar->inode->i_sb;
 	sbi = EXT4_SB(sb);
 
-	trace_mark(ext4_request_blocks, "dev %s flags %u len %u ino %lu "
+	trace_ext4_request_blocks(ar);
-		   "lblk %llu goal %llu lleft %llu lright %llu "
-		   "pleft %llu pright %llu ",
-		   sb->s_id, ar->flags, ar->len,
-		   ar->inode ? ar->inode->i_ino : 0,
-		   (unsigned long long) ar->logical,
-		   (unsigned long long) ar->goal,
-		   (unsigned long long) ar->lleft,
-		   (unsigned long long) ar->lright,
-		   (unsigned long long) ar->pleft,
-		   (unsigned long long) ar->pright);
 
 	/*
 	 * For delayed allocation, we could skip the ENOSPC and
@@ -4521,7 +4509,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
-	if (!ac) {
+	if (ac) {
+		ac->ac_sb = sb;
+		ac->ac_inode = ar->inode;
+	} else {
 		ar->len = 0;
 		*errp = -ENOMEM;
 		goto out1;
@@ -4594,18 +4585,7 @@ out3:
 						reserv_blks);
 	}
 
-	trace_mark(ext4_allocate_blocks,
+	trace_ext4_allocate_blocks(ar, (unsigned long long)block);
-		   "dev %s block %llu flags %u len %u ino %lu "
-		   "logical %llu goal %llu lleft %llu lright %llu "
-		   "pleft %llu pright %llu ",
-		   sb->s_id, (unsigned long long) block,
-		   ar->flags, ar->len, ar->inode ? ar->inode->i_ino : 0,
-		   (unsigned long long) ar->logical,
-		   (unsigned long long) ar->goal,
-		   (unsigned long long) ar->lleft,
-		   (unsigned long long) ar->lright,
-		   (unsigned long long) ar->pleft,
-		   (unsigned long long) ar->pright);
 
 	return block;
 }
@@ -4709,7 +4689,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
  * Main entry point into mballoc to free blocks
  */
 void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
-			unsigned long block, unsigned long count,
+			ext4_fsblk_t block, unsigned long count,
 			int metadata, unsigned long *freed)
 {
 	struct buffer_head *bitmap_bh = NULL;
@@ -4735,15 +4715,12 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
 	    block + count > ext4_blocks_count(es)) {
 		ext4_error(sb, __func__,
 			    "Freeing blocks not in datazone - "
-			    "block = %lu, count = %lu", block, count);
+			    "block = %llu, count = %lu", block, count);
 		goto error_return;
 	}
 
-	ext4_debug("freeing block %lu\n", block);
+	ext4_debug("freeing block %llu\n", block);
-	trace_mark(ext4_free_blocks,
+	trace_ext4_free_blocks(inode, block, count, metadata);
-		   "dev %s block %llu count %lu metadata %d ino %lu",
-		   sb->s_id, (unsigned long long) block, count, metadata,
-		   inode ? inode->i_ino : 0);
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 	if (ac) {
@@ -4784,7 +4761,7 @@ do_more:
 
 		ext4_error(sb, __func__,
 			   "Freeing blocks in system zone - "
-			   "Block = %lu, count = %lu", block, count);
+			   "Block = %llu, count = %lu", block, count);
 		/* err = 0. ext4_std_error should be a no op */
 		goto error_return;
 	}

fs/ext4/mballoc.h

@@ -19,7 +19,6 @@
 #include <linux/seq_file.h>
 #include <linux/version.h>
 #include <linux/blkdev.h>
-#include <linux/marker.h>
 #include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"

fs/ext4/migrate.c

@@ -458,6 +458,7 @@ int ext4_ext_migrate(struct inode *inode)
 	struct inode *tmp_inode = NULL;
 	struct list_blocks_struct lb;
 	unsigned long max_entries;
+	__u32 goal;
 
 	/*
 	 * If the filesystem does not support extents, or the inode
@@ -483,9 +484,10 @@ int ext4_ext_migrate(struct inode *inode)
 		retval = PTR_ERR(handle);
 		return retval;
 	}
-	tmp_inode = ext4_new_inode(handle,
+	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
-				inode->i_sb->s_root->d_inode,
+		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
-				S_IFREG);
+	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
+				   S_IFREG, 0, goal);
 	if (IS_ERR(tmp_inode)) {
 		retval = -ENOMEM;
 		ext4_journal_stop(handle);

fs/ext4/namei.c

@@ -1782,7 +1782,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode (handle, dir, mode);
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
@@ -1816,7 +1816,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode(handle, dir, mode);
+	inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
@@ -1853,7 +1853,8 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
+	inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
+			       &dentry->d_name, 0);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
@@ -2264,7 +2265,8 @@ retry:
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
+	inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
+			       &dentry->d_name, 0);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;

fs/ext4/super.c

@@ -37,7 +37,6 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/ctype.h>
-#include <linux/marker.h>
 #include <linux/log2.h>
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
@@ -47,6 +46,9 @@
 #include "xattr.h"
 #include "acl.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ext4.h>
+
 static int default_mb_history_length = 1000;
 
 module_param_named(default_mb_history_length, default_mb_history_length,
@@ -301,7 +303,7 @@ static void ext4_handle_error(struct super_block *sb)
 	if (!test_opt(sb, ERRORS_CONT)) {
 		journal_t *journal = EXT4_SB(sb)->s_journal;
 
-		EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
 		if (journal)
 			jbd2_journal_abort(journal, -EIO);
 	}
@@ -414,7 +416,7 @@ void ext4_abort(struct super_block *sb, const char *function,
 	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
-	EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+	EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
 	if (EXT4_SB(sb)->s_journal)
 		jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
@@ -1474,7 +1476,7 @@ set_qf_format:
 			break;
 #endif
 		case Opt_abort:
-			set_opt(sbi->s_mount_opt, ABORT);
+			sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
 			break;
 		case Opt_nobarrier:
 			clear_opt(sbi->s_mount_opt, BARRIER);
@@ -1653,7 +1655,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	ext4_commit_super(sb, 1);
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
-				"bpg=%lu, ipg=%lu, mo=%04lx]\n",
+				"bpg=%lu, ipg=%lu, mo=%04x]\n",
 			sb->s_blocksize,
 			sbi->s_groups_count,
 			EXT4_BLOCKS_PER_GROUP(sb),
@@ -2204,6 +2206,7 @@ EXT4_RO_ATTR(session_write_kbytes);
 EXT4_RO_ATTR(lifetime_write_kbytes);
 EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
 		 inode_readahead_blks_store, s_inode_readahead_blks);
+EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
 EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
 EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
@@ -2216,6 +2219,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(session_write_kbytes),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(inode_readahead_blks),
+	ATTR_LIST(inode_goal),
 	ATTR_LIST(mb_stats),
 	ATTR_LIST(mb_max_to_scan),
 	ATTR_LIST(mb_min_to_scan),
@@ -3346,7 +3350,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	int ret = 0;
 	tid_t target;
 
-	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
+	trace_ext4_sync_fs(sb, wait);
 	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
 		if (wait)
 			jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
@@ -3450,7 +3454,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if (sbi->s_mount_opt & EXT4_MOUNT_ABORT)
+	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 		ext4_abort(sb, __func__, "Abort forced by user");
 
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
@@ -3465,7 +3469,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
 		n_blocks_count > ext4_blocks_count(es)) {
-		if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) {
+		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
 			err = -EROFS;
 			goto restore_opts;
 		}

fs/jbd2/checkpoint.c

@@ -20,9 +20,9 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <trace/events/jbd2.h>
 
 /*
  * Unlink a buffer from a transaction checkpoint list.
@@ -358,8 +358,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 	 * journal straight away.
 	 */
 	result = jbd2_cleanup_journal_tail(journal);
-	trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d",
+	trace_jbd2_checkpoint(journal, result);
-		   journal->j_devname, result);
 	jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
 	if (result <= 0)
 		return result;

fs/jbd2/commit.c

@@ -16,7 +16,6 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -26,6 +25,7 @@
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
+#include <trace/events/jbd2.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -253,6 +253,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 		 * block allocation  with delalloc. We need to write
 		 * only allocated blocks here.
 		 */
+		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
 		err = journal_submit_inode_data_buffers(mapping);
 		if (!ret)
 			ret = err;
@@ -394,8 +395,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	commit_transaction = journal->j_running_transaction;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
-	trace_mark(jbd2_start_commit, "dev %s transaction %d",
+	trace_jbd2_start_commit(journal, commit_transaction);
-		   journal->j_devname, commit_transaction->t_tid);
 	jbd_debug(1, "JBD: starting commit of transaction %d\n",
 			commit_transaction->t_tid);
 
@@ -409,6 +409,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	if (commit_transaction->t_synchronous_commit)
 		write_op = WRITE_SYNC_PLUG;
+	trace_jbd2_commit_locking(journal, commit_transaction);
 	stats.u.run.rs_wait = commit_transaction->t_max_wait;
 	stats.u.run.rs_locked = jiffies;
 	stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
@@ -484,6 +485,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	jbd2_journal_switch_revoke_table(journal);
 
+	trace_jbd2_commit_flushing(journal, commit_transaction);
 	stats.u.run.rs_flushing = jiffies;
 	stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
 					       stats.u.run.rs_flushing);
@@ -520,6 +522,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	commit_transaction->t_state = T_COMMIT;
 	spin_unlock(&journal->j_state_lock);
 
+	trace_jbd2_commit_logging(journal, commit_transaction);
 	stats.u.run.rs_logging = jiffies;
 	stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
 						 stats.u.run.rs_logging);
@@ -1054,9 +1057,7 @@ restart_loop:
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
-	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
+	trace_jbd2_end_commit(journal, commit_transaction);
-		   journal->j_devname, commit_transaction->t_tid,
-		   journal->j_tail_sequence);
 	jbd_debug(1, "JBD: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 	if (to_free)

fs/jbd2/journal.c

@@ -38,6 +38,10 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/math64.h>
+#include <linux/hash.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/jbd2.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -2377,6 +2381,71 @@ static void __exit journal_exit(void)
 	jbd2_journal_destroy_caches();
 }
 
+/* 
+ * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 
+ * tracing infrastructure to map a dev_t to a device name.
+ *
+ * The caller should use rcu_read_lock() in order to make sure the
+ * device name stays valid until its done with it.  We use
+ * rcu_read_lock() as well to make sure we're safe in case the caller
+ * gets sloppy, and because rcu_read_lock() is cheap and can be safely
+ * nested.
+ */
+struct devname_cache {
+	struct rcu_head	rcu;
+	dev_t		device;
+	char		devname[BDEVNAME_SIZE];
+};
+#define CACHE_SIZE_BITS 6
+static struct devname_cache *devcache[1 << CACHE_SIZE_BITS];
+static DEFINE_SPINLOCK(devname_cache_lock);
+
+static void free_devcache(struct rcu_head *rcu)
+{
+	kfree(rcu);
+}
+
+const char *jbd2_dev_to_name(dev_t device)
+{
+	int	i = hash_32(device, CACHE_SIZE_BITS);
+	char	*ret;
+	struct block_device *bd;
+
+	rcu_read_lock();
+	if (devcache[i] && devcache[i]->device == device) {
+		ret = devcache[i]->devname;
+		rcu_read_unlock();
+		return ret;
+	}
+	rcu_read_unlock();
+
+	spin_lock(&devname_cache_lock);
+	if (devcache[i]) {
+		if (devcache[i]->device == device) {
+			ret = devcache[i]->devname;
+			spin_unlock(&devname_cache_lock);
+			return ret;
+		}
+		call_rcu(&devcache[i]->rcu, free_devcache);
+	}
+	devcache[i] = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
+	if (!devcache[i]) {
+		spin_unlock(&devname_cache_lock);
+		return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
+	}
+	devcache[i]->device = device;
+	bd = bdget(device);
+	if (bd) {
+		bdevname(bd, devcache[i]->devname);
+		bdput(bd);
+	} else
+		__bdevname(device, devcache[i]->devname);
+	ret = devcache[i]->devname;
+	spin_unlock(&devname_cache_lock);
+	return ret;
+}
+EXPORT_SYMBOL(jbd2_dev_to_name);
+
 MODULE_LICENSE("GPL");
 module_init(journal_init);
 module_exit(journal_exit);

fs/jbd2/transaction.c

@@ -1547,36 +1547,6 @@ out:
 	return;
 }
 
-/*
- * jbd2_journal_try_to_free_buffers() could race with
- * jbd2_journal_commit_transaction(). The later might still hold the
- * reference count to the buffers when inspecting them on
- * t_syncdata_list or t_locked_list.
- *
- * jbd2_journal_try_to_free_buffers() will call this function to
- * wait for the current transaction to finish syncing data buffers, before
- * try to free that buffer.
- *
- * Called with journal->j_state_lock hold.
- */
-static void jbd2_journal_wait_for_transaction_sync_data(journal_t *journal)
-{
-	transaction_t *transaction;
-	tid_t tid;
-
-	spin_lock(&journal->j_state_lock);
-	transaction = journal->j_committing_transaction;
-
-	if (!transaction) {
-		spin_unlock(&journal->j_state_lock);
-		return;
-	}
-
-	tid = transaction->t_tid;
-	spin_unlock(&journal->j_state_lock);
-	jbd2_log_wait_commit(journal, tid);
-}
-
 /**
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
@@ -1649,25 +1619,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 
 	ret = try_to_free_buffers(page);
 
-	/*
-	 * There are a number of places where jbd2_journal_try_to_free_buffers()
-	 * could race with jbd2_journal_commit_transaction(), the later still
-	 * holds the reference to the buffers to free while processing them.
-	 * try_to_free_buffers() failed to free those buffers. Some of the
-	 * caller of releasepage() request page buffers to be dropped, otherwise
-	 * treat the fail-to-free as errors (such as generic_file_direct_IO())
-	 *
-	 * So, if the caller of try_to_release_page() wants the synchronous
-	 * behaviour(i.e make sure buffers are dropped upon return),
-	 * let's wait for the current transaction to finish flush of
-	 * dirty data buffers, then try to free those buffers again,
-	 * with the journal locked.
-	 */
-	if (ret == 0 && (gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)) {
-		jbd2_journal_wait_for_transaction_sync_data(journal);
-		ret = try_to_free_buffers(page);
-	}
-
 busy:
 	return ret;
 }

include/linux/jbd2.h

@@ -1315,6 +1315,12 @@ extern int jbd_blocks_per_page(struct inode *inode);
 #define BUFFER_TRACE2(bh, bh2, info)	do {} while (0)
 #define JBUFFER_TRACE(jh, info)	do {} while (0)
 
+/* 
+ * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 
+ * tracing infrastructure to map a dev_t to a device name.
+ */
+extern const char *jbd2_dev_to_name(dev_t device);
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _LINUX_JBD2_H */

include/trace/events/ext4.h

@@ -0,0 +1,719 @@
+#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EXT4_H
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ext4
+
+#include <linux/writeback.h>
+#include "../../../fs/ext4/ext4.h"
+#include "../../../fs/ext4/mballoc.h"
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(ext4_free_inode,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	uid_t,	uid			)
+		__field(	gid_t,	gid			)
+		__field(	blkcnt_t, blocks		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->uid	= inode->i_uid;
+		__entry->gid	= inode->i_gid;
+		__entry->blocks	= inode->i_blocks;
+	),
+
+	TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid, __entry->blocks)
+);
+
+TRACE_EVENT(ext4_request_inode,
+	TP_PROTO(struct inode *dir, int mode),
+
+	TP_ARGS(dir, mode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	dir			)
+		__field(	umode_t, mode			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= dir->i_sb->s_dev;
+		__entry->dir	= dir->i_ino;
+		__entry->mode	= mode;
+	),
+
+	TP_printk("dev %s dir %lu mode %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->dir, __entry->mode)
+);
+
+TRACE_EVENT(ext4_allocate_inode,
+	TP_PROTO(struct inode *inode, struct inode *dir, int mode),
+
+	TP_ARGS(inode, dir, mode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	ino_t,	dir			)
+		__field(	umode_t, mode			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->dir	= dir->i_ino;
+		__entry->mode	= mode;
+	),
+
+	TP_printk("dev %s ino %lu dir %lu mode %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->dir, __entry->mode)
+);
+
+TRACE_EVENT(ext4_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u flags %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->flags)
+);
+
+TRACE_EVENT(ext4_ordered_write_end,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+			unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, copied		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->copied)
+);
+
+TRACE_EVENT(ext4_writeback_write_end,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, copied		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->copied)
+);
+
+TRACE_EVENT(ext4_journalled_write_end,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, copied		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->copied)
+);
+
+TRACE_EVENT(ext4_da_writepage,
+	TP_PROTO(struct inode *inode, struct page *page),
+
+	TP_ARGS(inode, page),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	pgoff_t, index			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->index	= page->index;
+	),
+
+	TP_printk("dev %s ino %lu page_index %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+);
+
+TRACE_EVENT(ext4_da_writepages,
+	TP_PROTO(struct inode *inode, struct writeback_control *wbc),
+
+	TP_ARGS(inode, wbc),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	long,	nr_to_write		)
+		__field(	long,	pages_skipped		)
+		__field(	loff_t,	range_start		)
+		__field(	loff_t,	range_end		)
+		__field(	char,	nonblocking		)
+		__field(	char,	for_kupdate		)
+		__field(	char,	for_reclaim		)
+		__field(	char,	for_writepages		)
+		__field(	char,	range_cyclic		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->nr_to_write	= wbc->nr_to_write;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->range_start	= wbc->range_start;
+		__entry->range_end	= wbc->range_end;
+		__entry->nonblocking	= wbc->nonblocking;
+		__entry->for_kupdate	= wbc->for_kupdate;
+		__entry->for_reclaim	= wbc->for_reclaim;
+		__entry->for_writepages	= wbc->for_writepages;
+		__entry->range_cyclic	= wbc->range_cyclic;
+	),
+
+	TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d for_writepages %d range_cyclic %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write,
+		  __entry->pages_skipped, __entry->range_start,
+		  __entry->range_end, __entry->nonblocking,
+		  __entry->for_kupdate, __entry->for_reclaim,
+		  __entry->for_writepages, __entry->range_cyclic)
+);
+
+TRACE_EVENT(ext4_da_writepages_result,
+	TP_PROTO(struct inode *inode, struct writeback_control *wbc,
+			int ret, int pages_written),
+
+	TP_ARGS(inode, wbc, ret, pages_written),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	int,	ret			)
+		__field(	int,	pages_written		)
+		__field(	long,	pages_skipped		)
+		__field(	char,	encountered_congestion	)
+		__field(	char,	more_io			)	
+		__field(	char,	no_nrwrite_index_update )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->ret		= ret;
+		__entry->pages_written	= pages_written;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->encountered_congestion	= wbc->encountered_congestion;
+		__entry->more_io	= wbc->more_io;
+		__entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+	),
+
+	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->ret,
+		  __entry->pages_written, __entry->pages_skipped,
+		  __entry->encountered_congestion, __entry->more_io,
+		  __entry->no_nrwrite_index_update)
+);
+
+TRACE_EVENT(ext4_da_write_begin,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+			unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u flags %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->flags)
+);
+
+TRACE_EVENT(ext4_da_write_end,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+			unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	pos			)
+		__field(	unsigned int, len		)
+		__field(	unsigned int, copied		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
+		  __entry->copied)
+);
+
+TRACE_EVENT(ext4_normal_writepage,
+	TP_PROTO(struct inode *inode, struct page *page),
+
+	TP_ARGS(inode, page),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	pgoff_t, index			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->index	= page->index;
+	),
+
+	TP_printk("dev %s ino %lu page_index %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+);
+
+TRACE_EVENT(ext4_journalled_writepage,
+	TP_PROTO(struct inode *inode, struct page *page),
+
+	TP_ARGS(inode, page),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	pgoff_t, index			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->index	= page->index;
+	),
+
+	TP_printk("dev %s ino %lu page_index %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+);
+
+TRACE_EVENT(ext4_discard_blocks,
+	TP_PROTO(struct super_block *sb, unsigned long long blk,
+			unsigned long long count),
+
+	TP_ARGS(sb, blk, count),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u64,	blk			)
+		__field(	__u64,	count			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->blk	= blk;
+		__entry->count	= count;
+	),
+
+	TP_printk("dev %s blk %llu count %llu",
+		  jbd2_dev_to_name(__entry->dev), __entry->blk, __entry->count)
+);
+
+TRACE_EVENT(ext4_mb_new_inode_pa,
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa),
+
+	TP_ARGS(ac, pa),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	pa_pstart		)
+		__field(	__u32,	pa_len			)
+		__field(	__u64,	pa_lstart		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->pa_pstart	= pa->pa_pstart;
+		__entry->pa_len		= pa->pa_len;
+		__entry->pa_lstart	= pa->pa_lstart;
+	),
+
+	TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart,
+		  __entry->pa_len, __entry->pa_lstart)
+);
+
+TRACE_EVENT(ext4_mb_new_group_pa,
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa),
+
+	TP_ARGS(ac, pa),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	pa_pstart		)
+		__field(	__u32,	pa_len			)
+		__field(	__u64,	pa_lstart		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->pa_pstart	= pa->pa_pstart;
+		__entry->pa_len		= pa->pa_len;
+		__entry->pa_lstart	= pa->pa_lstart;
+	),
+
+	TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart,
+		  __entry->pa_len, __entry->pa_lstart)
+);
+
+TRACE_EVENT(ext4_mb_release_inode_pa,
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa,
+		 unsigned long long block, unsigned int count),
+
+	TP_ARGS(ac, pa, block, count),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	block			)
+		__field(	__u32,	count			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->block		= block;
+		__entry->count		= count;
+	),
+
+	TP_printk("dev %s ino %lu block %llu count %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
+		  __entry->count)
+);
+
+TRACE_EVENT(ext4_mb_release_group_pa,
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa),
+
+	TP_ARGS(ac, pa),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	pa_pstart		)
+		__field(	__u32,	pa_len			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev		= ac->ac_sb->s_dev;
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->pa_pstart	= pa->pa_pstart;
+		__entry->pa_len		= pa->pa_len;
+	),
+
+	TP_printk("dev %s pstart %llu len %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->pa_pstart, __entry->pa_len)
+);
+
+TRACE_EVENT(ext4_discard_preallocations,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+	),
+
+	TP_printk("dev %s ino %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino)
+);
+
+TRACE_EVENT(ext4_mb_discard_preallocations,
+	TP_PROTO(struct super_block *sb, int needed),
+
+	TP_ARGS(sb, needed),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	needed			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->needed	= needed;
+	),
+
+	TP_printk("dev %s needed %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->needed)
+);
+
+TRACE_EVENT(ext4_request_blocks,
+	TP_PROTO(struct ext4_allocation_request *ar),
+
+	TP_ARGS(ar),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	unsigned int, flags		)
+		__field(	unsigned int, len		)
+		__field(	__u64,  logical			)
+		__field(	__u64,	goal			)
+		__field(	__u64,	lleft			)
+		__field(	__u64,	lright			)
+		__field(	__u64,	pleft			)
+		__field(	__u64,	pright			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= ar->inode->i_sb->s_dev;
+		__entry->ino	= ar->inode->i_ino;
+		__entry->flags	= ar->flags;
+		__entry->len	= ar->len;
+		__entry->logical = ar->logical;
+		__entry->goal	= ar->goal;
+		__entry->lleft	= ar->lleft;
+		__entry->lright	= ar->lright;
+		__entry->pleft	= ar->pleft;
+		__entry->pright	= ar->pright;
+	),
+
+	TP_printk("dev %s ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
+		  __entry->len,
+		  (unsigned long long) __entry->logical,
+		  (unsigned long long) __entry->goal,
+		  (unsigned long long) __entry->lleft,
+		  (unsigned long long) __entry->lright,
+		  (unsigned long long) __entry->pleft,
+		  (unsigned long long) __entry->pright)
+);
+
+TRACE_EVENT(ext4_allocate_blocks,
+	TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block),
+
+	TP_ARGS(ar, block),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	block			)
+		__field(	unsigned int, flags		)
+		__field(	unsigned int, len		)
+		__field(	__u64,  logical			)
+		__field(	__u64,	goal			)
+		__field(	__u64,	lleft			)
+		__field(	__u64,	lright			)
+		__field(	__u64,	pleft			)
+		__field(	__u64,	pright			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= ar->inode->i_sb->s_dev;
+		__entry->ino	= ar->inode->i_ino;
+		__entry->block	= block;
+		__entry->flags	= ar->flags;
+		__entry->len	= ar->len;
+		__entry->logical = ar->logical;
+		__entry->goal	= ar->goal;
+		__entry->lleft	= ar->lleft;
+		__entry->lright	= ar->lright;
+		__entry->pleft	= ar->pleft;
+		__entry->pright	= ar->pright;
+	),
+
+	TP_printk("dev %s ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
+		  __entry->len, __entry->block,
+		  (unsigned long long) __entry->logical,
+		  (unsigned long long) __entry->goal,
+		  (unsigned long long) __entry->lleft,
+		  (unsigned long long) __entry->lright,
+		  (unsigned long long) __entry->pleft,
+		  (unsigned long long) __entry->pright)
+);
+
+TRACE_EVENT(ext4_free_blocks,
+	TP_PROTO(struct inode *inode, __u64 block, unsigned long count,
+			int metadata),
+
+	TP_ARGS(inode, block, count, metadata),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	__u64,	block			)
+		__field(	unsigned long,	count		)
+		__field(	int,	metadata		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->block		= block;
+		__entry->count		= count;
+		__entry->metadata	= metadata;
+	),
+
+	TP_printk("dev %s ino %lu block %llu count %lu metadata %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
+		  __entry->count, __entry->metadata)
+);
+
+TRACE_EVENT(ext4_sync_file,
+	TP_PROTO(struct file *file, struct dentry *dentry, int datasync),
+
+	TP_ARGS(file, dentry, datasync),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	ino_t,	parent			)
+		__field(	int,	datasync		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= dentry->d_inode->i_sb->s_dev;
+		__entry->ino		= dentry->d_inode->i_ino;
+		__entry->datasync	= datasync;
+		__entry->parent		= dentry->d_parent->d_inode->i_ino;
+	),
+
+	TP_printk("dev %s ino %ld parent %ld datasync %d ",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->parent,
+		  __entry->datasync)
+);
+
+TRACE_EVENT(ext4_sync_fs,
+	TP_PROTO(struct super_block *sb, int wait),
+
+	TP_ARGS(sb, wait),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	wait			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->wait	= wait;
+	),
+
+	TP_printk("dev %s wait %d", jbd2_dev_to_name(__entry->dev),
+		  __entry->wait)
+);
+
+#endif /* _TRACE_EXT4_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/trace/events/jbd2.h

@@ -0,0 +1,168 @@
+#if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_JBD2_H
+
+#include <linux/jbd2.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM jbd2
+
+TRACE_EVENT(jbd2_checkpoint,
+
+	TP_PROTO(journal_t *journal, int result),
+
+	TP_ARGS(journal, result),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int,	result			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->result		= result;
+	),
+
+	TP_printk("dev %s result %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->result)
+);
+
+TRACE_EVENT(jbd2_start_commit,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	char,	sync_commit		  )
+		__field(	int,	transaction		  )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->sync_commit = commit_transaction->t_synchronous_commit;
+		__entry->transaction	= commit_transaction->t_tid;
+	),
+
+	TP_printk("dev %s transaction %d sync %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit)
+);
+
+TRACE_EVENT(jbd2_commit_locking,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	char,	sync_commit		  )
+		__field(	int,	transaction		  )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->sync_commit = commit_transaction->t_synchronous_commit;
+		__entry->transaction	= commit_transaction->t_tid;
+	),
+
+	TP_printk("dev %s transaction %d sync %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit)
+);
+
+TRACE_EVENT(jbd2_commit_flushing,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	char,	sync_commit		  )
+		__field(	int,	transaction		  )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->sync_commit = commit_transaction->t_synchronous_commit;
+		__entry->transaction	= commit_transaction->t_tid;
+	),
+
+	TP_printk("dev %s transaction %d sync %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit)
+);
+
+TRACE_EVENT(jbd2_commit_logging,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	char,	sync_commit		  )
+		__field(	int,	transaction		  )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->sync_commit = commit_transaction->t_synchronous_commit;
+		__entry->transaction	= commit_transaction->t_tid;
+	),
+
+	TP_printk("dev %s transaction %d sync %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit)
+);
+
+TRACE_EVENT(jbd2_end_commit,
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	char,	sync_commit		  )
+		__field(	int,	transaction		  )
+		__field(	int,	head		  	  )
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->sync_commit = commit_transaction->t_synchronous_commit;
+		__entry->transaction	= commit_transaction->t_tid;
+		__entry->head		= journal->j_tail_sequence;
+	),
+
+	TP_printk("dev %s transaction %d sync %d head %d",
+		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
+		  __entry->sync_commit, __entry->head)
+);
+
+TRACE_EVENT(jbd2_submit_inode_data,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+	),
+
+	TP_printk("dev %s ino %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->ino)
+);
+
+#endif /* _TRACE_JBD2_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>