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",
-		   inode->i_sb->s_id, datasync, inode->i_ino,
-		   dentry->d_parent->d_inode->i_ino);
+	trace_ext4_sync_file(file, dentry, datasync);
 
 	/*
 	 * 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,
-		   "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);
+	trace_ext4_free_inode(inode);
 
 	/*
 	 * 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 @@ static int ext4_claim_inode(struct super_block *sb,
  * 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,
-		   dir->i_ino, mode);
+	trace_ext4_request_inode(dir, 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 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 	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 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 		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 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
-	trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d",
-		   sb->s_id, inode->i_ino, dir->i_ino, mode);
+	trace_ext4_allocate_inode(inode, dir, mode);
 	goto really_out;
 fail:
 	ext4_std_error(sb, err);

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 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		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",
-			   sb->s_id, (unsigned long long) discard_block,
-			   entry->count);
+		trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
+					  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,
-		   "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);
+	trace_ext4_mb_new_inode_pa(ac, pa);
 
 	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);
-	trace_mark(ext4_mb_new_group_pa, "dev %s pstart %llu len %u lstart %u",
-		   sb->s_id, pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+			pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+	trace_ext4_mb_new_group_pa(ac, pa);
 
 	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,
-			   "dev %s ino %lu block %llu count %u",
-			   sb->s_id, pa->pa_inode->i_ino, grp_blk_start + bit,
-			   next - bit);
+		trace_ext4_mb_release_inode_pa(ac, pa, 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",
-		   sb->s_id, pa->pa_pstart, pa->pa_len);
+	trace_ext4_mb_release_group_pa(ac, pa);
 	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,
-		   inode->i_ino);
+	trace_ext4_discard_preallocations(inode);
 
 	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",
-		   sb->s_id, needed);
+	trace_ext4_mb_discard_preallocations(sb, 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 "
-		   "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);
+	trace_ext4_request_blocks(ar);
 
 	/*
 	 * 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 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 						reserv_blks);
 	}
 
-	trace_mark(ext4_allocate_blocks,
-		   "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);
+	trace_ext4_allocate_blocks(ar, (unsigned long long)block);
 
 	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);
-	trace_mark(ext4_free_blocks,
-		   "dev %s block %llu count %lu metadata %d ino %lu",
-		   sb->s_id, (unsigned long long) block, count, metadata,
-		   inode ? inode->i_ino : 0);
+	ext4_debug("freeing block %llu\n", block);
+	trace_ext4_free_blocks(inode, block, count, metadata);
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 	if (ac) {
@@ -4784,7 +4761,7 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
 
 		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,
-				inode->i_sb->s_root->d_inode,
-				S_IFREG);
+	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
+		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
+	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 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
 	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 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 	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 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	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 @@ static int ext4_symlink(struct inode *dir,
 	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 @@ static int parse_options(char *options, struct super_block *sb,
 			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",
-		   journal->j_devname, result);
+	trace_jbd2_checkpoint(journal, 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",
-		   journal->j_devname, commit_transaction->t_tid);
+	trace_jbd2_start_commit(journal, commit_transaction);
 	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 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
-	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
-		   journal->j_devname, commit_transaction->t_tid,
-		   journal->j_tail_sequence);
+	trace_jbd2_end_commit(journal, commit_transaction);
 	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 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
 	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/jbd2.h

+#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>