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

Pull ext4 updates from Ted Ts'o:
 "Fix some bugs in converting ext4 to use the new mount API, as well as
  more bug fixes and clean ups in the ext4 fast_commit feature (most
  notably, in the tracepoints).

  In the jbd2 layer, the t_handle_lock spinlock has been removed, with
  the last place where it was actually needed replaced with an atomic
  cmpxchg"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (35 commits)
  ext4: fix kernel doc warnings
  ext4: fix remaining two trace events to use same printk convention
  ext4: add commit tid info in ext4_fc_commit_start/stop trace events
  ext4: add commit_tid info in jbd debug log
  ext4: add transaction tid info in fc_track events
  ext4: add new trace event in ext4_fc_cleanup
  ext4: return early for non-eligible fast_commit track events
  ext4: do not call FC trace event in ext4_fc_commit() if FS does not support FC
  ext4: convert ext4_fc_track_dentry type events to use event class
  ext4: fix ext4_fc_stats trace point
  ext4: remove unused enum EXT4_FC_COMMIT_FAILED
  ext4: warn when dirtying page w/o buffers in data=journal mode
  doc: fixed a typo in ext4 documentation
  ext4: make mb_optimize_scan performance mount option work with extents
  ext4: make mb_optimize_scan option work with set/unset mount cmd
  ext4: don't BUG if someone dirty pages without asking ext4 first
  ext4: remove redundant assignment to variable split_flag1
  ext4: fix underflow in ext4_max_bitmap_size()
  ext4: fix ext4_mb_clear_bb() kernel-doc comment
  ext4: fix fs corruption when tring to remove a non-empty directory with IO error
  ...

Documentation/filesystems/ext4/blocks.rst

@@ -39,7 +39,7 @@ For 32-bit filesystems, limits are as follows:
      - 4TiB
      - 8TiB
      - 16TiB
-     - 256PiB
+     - 256TiB
    * - Blocks Per Block Group
      - 8,192
      - 16,384

fs/ext4/balloc.c

@@ -411,6 +411,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
  * ext4_read_block_bitmap_nowait()
  * @sb:			super block
  * @block_group:	given block group
+ * @ignore_locked:	ignore locked buffers
  *
  * Read the bitmap for a given block_group,and validate the
  * bits for block/inode/inode tables are set in the bitmaps

fs/ext4/block_validity.c

@@ -292,15 +292,10 @@ void ext4_release_system_zone(struct super_block *sb)
 		call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
 }
 
-/*
- * Returns 1 if the passed-in block region (start_blk,
- * start_blk+count) is valid; 0 if some part of the block region
- * overlaps with some other filesystem metadata blocks.
- */
-int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
-			  unsigned int count)
+int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+				ext4_fsblk_t start_blk, unsigned int count)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_system_blocks *system_blks;
 	struct ext4_system_zone *entry;
 	struct rb_node *n;
@@ -329,6 +324,8 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = n->rb_right;
 		else {
+			ret = 0;
+			if (inode)
 				ret = (entry->ino == inode->i_ino);
 			break;
 		}
@@ -338,6 +335,17 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 	return ret;
 }
 
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+			  unsigned int count)
+{
+	return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count);
+}
+
 int ext4_check_blockref(const char *function, unsigned int line,
 			struct inode *inode, __le32 *p, unsigned int max)
 {

fs/ext4/ext4.h

@@ -1046,6 +1046,8 @@ struct ext4_inode_info {
 
 	/* Fast commit related info */
 
+	/* For tracking dentry create updates */
+	struct list_head i_fc_dilist;
 	struct list_head i_fc_list;	/*
 					 * inodes that need fast commit
 					 * protected by sbi->s_fc_lock.
@@ -1279,7 +1281,7 @@ struct ext4_inode_info {
 #define ext4_find_next_zero_bit		find_next_zero_bit_le
 #define ext4_find_next_bit		find_next_bit_le
 
-extern void ext4_set_bits(void *bm, int cur, int len);
+extern void mb_set_bits(void *bm, int cur, int len);
 
 /*
  * Maximal mount counts between two filesystem checks
@@ -3707,6 +3709,9 @@ extern int ext4_inode_block_valid(struct inode *inode,
 				  unsigned int count);
 extern int ext4_check_blockref(const char *, unsigned int,
 			       struct inode *, __le32 *, unsigned int);
+extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+				ext4_fsblk_t start_blk, unsigned int count);
+
 
 /* extents.c */
 struct ext4_ext_path;

fs/ext4/extents.c

@@ -3368,7 +3368,6 @@ static int ext4_split_extent(handle_t *handle,
 		return -EFSCORRUPTED;
 	}
 	unwritten = ext4_ext_is_unwritten(ex);
-	split_flag1 = 0;
 
 	if (map->m_lblk >= ee_block) {
 		split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;

fs/ext4/fast_commit.h

@@ -93,7 +93,6 @@ enum {
 	EXT4_FC_REASON_RENAME_DIR,
 	EXT4_FC_REASON_FALLOC_RANGE,
 	EXT4_FC_REASON_INODE_JOURNAL_DATA,
-	EXT4_FC_COMMIT_FAILED,
 	EXT4_FC_REASON_MAX
 };
 
@@ -109,6 +108,7 @@ struct ext4_fc_dentry_update {
 	struct qstr fcd_name;	/* Dirent name */
 	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
 	struct list_head fcd_list;
+	struct list_head fcd_dilist;
 };
 
 struct ext4_fc_stats {

fs/ext4/inline.c

@@ -1783,19 +1783,20 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
 	void *inline_pos;
 	unsigned int offset;
 	struct ext4_dir_entry_2 *de;
-	bool ret = true;
+	bool ret = false;
 
 	err = ext4_get_inode_loc(dir, &iloc);
 	if (err) {
 		EXT4_ERROR_INODE_ERR(dir, -err,
 				     "error %d getting inode %lu block",
 				     err, dir->i_ino);
-		return true;
+		return false;
 	}
 
 	down_read(&EXT4_I(dir)->xattr_sem);
 	if (!ext4_has_inline_data(dir)) {
 		*has_inline_data = 0;
+		ret = true;
 		goto out;
 	}
 
@@ -1804,7 +1805,6 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
 		ext4_warning(dir->i_sb,
 			     "bad inline directory (dir #%lu) - no `..'",
 			     dir->i_ino);
-		ret = true;
 		goto out;
 	}
 
@@ -1823,16 +1823,15 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
 				     dir->i_ino, le32_to_cpu(de->inode),
 				     le16_to_cpu(de->rec_len), de->name_len,
 				     inline_size);
-			ret = true;
 			goto out;
 		}
 		if (le32_to_cpu(de->inode)) {
-			ret = false;
 			goto out;
 		}
 		offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
 	}
 
+	ret = true;
 out:
 	up_read(&EXT4_I(dir)->xattr_sem);
 	brelse(iloc.bh);

fs/ext4/inode.c

@@ -1993,6 +1993,15 @@ static int ext4_writepage(struct page *page,
 	else
 		len = PAGE_SIZE;
 
+	/* Should never happen but for bugs in other kernel subsystems */
+	if (!page_has_buffers(page)) {
+		ext4_warning_inode(inode,
+		   "page %lu does not have buffers attached", page->index);
+		ClearPageDirty(page);
+		unlock_page(page);
+		return 0;
+	}
+
 	page_bufs = page_buffers(page);
 	/*
 	 * We cannot do block allocation or other extent handling in this
@@ -2594,6 +2603,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			wait_on_page_writeback(page);
 			BUG_ON(PageWriteback(page));
 
+			/*
+			 * Should never happen but for buggy code in
+			 * other subsystems that call
+			 * set_page_dirty() without properly warning
+			 * the file system first.  See [1] for more
+			 * information.
+			 *
+			 * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
+			 */
+			if (!page_has_buffers(page)) {
+				ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
+				ClearPageDirty(page);
+				unlock_page(page);
+				continue;
+			}
+
 			if (mpd->map.m_len == 0)
 				mpd->first_page = page->index;
 			mpd->next_page = page->index + 1;
@@ -3548,10 +3573,11 @@ const struct iomap_ops ext4_iomap_report_ops = {
 };
 
 /*
- * Pages can be marked dirty completely asynchronously from ext4's journalling
- * activity.  By filemap_sync_pte(), try_to_unmap_one(), etc.  We cannot do
- * much here because ->set_page_dirty is called under VFS locks.  The page is
- * not necessarily locked.
+ * Whenever the page is being dirtied, corresponding buffers should already be
+ * attached to the transaction (we take care of this in ext4_page_mkwrite() and
+ * ext4_write_begin()). However we cannot move buffers to dirty transaction
+ * lists here because ->set_page_dirty is called under VFS locks and the page
+ * is not necessarily locked.
  *
  * We cannot just dirty the page and leave attached buffers clean, because the
  * buffers' dirty state is "definitive".  We cannot just set the buffers dirty
@@ -3562,6 +3588,7 @@ const struct iomap_ops ext4_iomap_report_ops = {
  */
 static int ext4_journalled_set_page_dirty(struct page *page)
 {
+	WARN_ON_ONCE(!page_has_buffers(page));
 	SetPageChecked(page);
 	return __set_page_dirty_nobuffers(page);
 }

fs/ext4/ioctl.c

@@ -269,7 +269,7 @@ int ext4_update_superblocks_fn(struct super_block *sb,
 	return err ? err : 0;
 }
 
-/**
+/*
  * Swap memory between @a and @b for @len bytes.
  *
  * @a:          pointer to first memory area
@@ -290,7 +290,7 @@ static void memswap(void *a, void *b, size_t len)
 	}
 }
 
-/**
+/*
  * Swap i_data and associated attributes between @inode1 and @inode2.
  * This function is used for the primary swap between inode1 and inode2
  * and also to revert this primary swap in case of errors.
@@ -344,7 +344,7 @@ void ext4_reset_inode_seed(struct inode *inode)
 	ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen));
 }
 
-/**
+/*
  * Swap the information from the given @inode and the inode
  * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
  * important fields of the inodes.

fs/ext4/namei.c

@@ -2997,14 +2997,14 @@ bool ext4_empty_dir(struct inode *inode)
 	if (inode->i_size < ext4_dir_rec_len(1, NULL) +
 					ext4_dir_rec_len(2, NULL)) {
 		EXT4_ERROR_INODE(inode, "invalid size");
-		return true;
+		return false;
 	}
 	/* The first directory block must not be a hole,
 	 * so treat it as DIRENT_HTREE
 	 */
 	bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
 	if (IS_ERR(bh))
-		return true;
+		return false;
 
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
@@ -3012,7 +3012,7 @@ bool ext4_empty_dir(struct inode *inode)
 	    le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) {
 		ext4_warning_inode(inode, "directory missing '.'");
 		brelse(bh);
-		return true;
+		return false;
 	}
 	offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
 	de = ext4_next_entry(de, sb->s_blocksize);
@@ -3021,7 +3021,7 @@ bool ext4_empty_dir(struct inode *inode)
 	    le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
 		ext4_warning_inode(inode, "directory missing '..'");
 		brelse(bh);
-		return true;
+		return false;
 	}
 	offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
 	while (offset < inode->i_size) {
@@ -3035,7 +3035,7 @@ bool ext4_empty_dir(struct inode *inode)
 				continue;
 			}
 			if (IS_ERR(bh))
-				return true;
+				return false;
 		}
 		de = (struct ext4_dir_entry_2 *) (bh->b_data +
 					(offset & (sb->s_blocksize - 1)));
@@ -3891,12 +3891,19 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 		ext4_fc_mark_ineligible(old.inode->i_sb,
 			EXT4_FC_REASON_RENAME_DIR, handle);
 	} else {
+		struct super_block *sb = old.inode->i_sb;
+
 		if (new.inode)
 			ext4_fc_track_unlink(handle, new.dentry);
+		if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+		    !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+		    !(ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE))) {
 			__ext4_fc_track_link(handle, old.inode, new.dentry);
 			__ext4_fc_track_unlink(handle, old.inode, old.dentry);
 			if (whiteout)
-			__ext4_fc_track_create(handle, whiteout, old.dentry);
+				__ext4_fc_track_create(handle, whiteout,
+						       old.dentry);
+		}
 	}
 
 	if (new.inode) {

fs/ext4/resize.c

@@ -14,6 +14,7 @@
 
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/jiffies.h>
 
 #include "ext4_jbd2.h"
 
@@ -483,7 +484,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 		}
 		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n",
 			   first_cluster, first_cluster - start, count2);
-		ext4_set_bits(bh->b_data, first_cluster - start, count2);
+		mb_set_bits(bh->b_data, first_cluster - start, count2);
 
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
 		brelse(bh);
@@ -632,7 +633,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 		if (overhead != 0) {
 			ext4_debug("mark backup superblock %#04llx (+0)\n",
 				   start);
-			ext4_set_bits(bh->b_data, 0,
+			mb_set_bits(bh->b_data, 0,
 				      EXT4_NUM_B2C(sbi, overhead));
 		}
 		ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count),
@@ -2100,7 +2101,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 	 */
 	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
 					      flexbg_size)) {
-		if (jiffies - last_update_time > HZ * 10) {
+		if (time_is_before_jiffies(last_update_time + HZ * 10)) {
 			if (last_update_time)
 				ext4_msg(sb, KERN_INFO,
 					 "resized to %llu blocks",

fs/ext4/super.c

@@ -2021,12 +2021,12 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb, char *arg)
 #define EXT4_SPEC_s_commit_interval		(1 << 16)
 #define EXT4_SPEC_s_fc_debug_max_replay		(1 << 17)
 #define EXT4_SPEC_s_sb_block			(1 << 18)
+#define EXT4_SPEC_mb_optimize_scan		(1 << 19)
 
 struct ext4_fs_context {
 	char		*s_qf_names[EXT4_MAXQUOTAS];
 	char		*test_dummy_enc_arg;
 	int		s_jquota_fmt;	/* Format of quota to use */
-	int		mb_optimize_scan;
 #ifdef CONFIG_EXT4_DEBUG
 	int s_fc_debug_max_replay;
 #endif
@@ -2045,8 +2045,8 @@ struct ext4_fs_context {
 	unsigned int	mask_s_mount_opt;
 	unsigned int	vals_s_mount_opt2;
 	unsigned int	mask_s_mount_opt2;
-	unsigned int	vals_s_mount_flags;
-	unsigned int	mask_s_mount_flags;
+	unsigned long	vals_s_mount_flags;
+	unsigned long	mask_s_mount_flags;
 	unsigned int	opt_flags;	/* MOPT flags */
 	unsigned int	spec;
 	u32		s_max_batch_time;
@@ -2149,23 +2149,36 @@ static inline void ctx_set_##name(struct ext4_fs_context *ctx,		\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name |= flag;					\
-}									\
+}
+
+#define EXT4_CLEAR_CTX(name)						\
 static inline void ctx_clear_##name(struct ext4_fs_context *ctx,	\
 				    unsigned long flag)			\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name &= ~flag;					\
-}									\
+}
+
+#define EXT4_TEST_CTX(name)						\
 static inline unsigned long						\
 ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag)	\
 {									\
 	return (ctx->vals_s_##name & flag);				\
-}									\
+}
 
-EXT4_SET_CTX(flags);
+EXT4_SET_CTX(flags); /* set only */
 EXT4_SET_CTX(mount_opt);
+EXT4_CLEAR_CTX(mount_opt);
+EXT4_TEST_CTX(mount_opt);
 EXT4_SET_CTX(mount_opt2);
-EXT4_SET_CTX(mount_flags);
+EXT4_CLEAR_CTX(mount_opt2);
+EXT4_TEST_CTX(mount_opt2);
+
+static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit)
+{
+	set_bit(bit, &ctx->mask_s_mount_flags);
+	set_bit(bit, &ctx->vals_s_mount_flags);
+}
 
 static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
@@ -2235,7 +2248,7 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 			 param->key);
 		return 0;
 	case Opt_abort:
-		ctx_set_mount_flags(ctx, EXT4_MF_FS_ABORTED);
+		ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
 		return 0;
 	case Opt_i_version:
 		ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
@@ -2451,12 +2464,17 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 			ctx_clear_mount_opt(ctx, m->mount_opt);
 		return 0;
 	case Opt_mb_optimize_scan:
-		if (result.int_32 != 0 && result.int_32 != 1) {
+		if (result.int_32 == 1) {
+			ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+			ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+		} else if (result.int_32 == 0) {
+			ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+			ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+		} else {
 			ext4_msg(NULL, KERN_WARNING,
 				 "mb_optimize_scan should be set to 0 or 1.");
 			return -EINVAL;
 		}
-		ctx->mb_optimize_scan = result.int_32;
 		return 0;
 	}
 
@@ -3468,8 +3486,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files)
  */
 static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 {
-	unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS;
+	loff_t upper_limit, res = EXT4_NDIR_BLOCKS;
 	int meta_blocks;
+	unsigned int ppb = 1 << (bits - 2);
 
 	/*
 	 * This is calculated to be the largest file size for a dense, block
@@ -3501,27 +3520,42 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 
 	}
 
+	/* Compute how many blocks we can address by block tree */
+	res += ppb;
+	res += ppb * ppb;
+	res += ((loff_t)ppb) * ppb * ppb;
+	/* Compute how many metadata blocks are needed */
+	meta_blocks = 1;
+	meta_blocks += 1 + ppb;
+	meta_blocks += 1 + ppb + ppb * ppb;
+	/* Does block tree limit file size? */
+	if (res + meta_blocks <= upper_limit)
+		goto check_lfs;
+
+	res = upper_limit;
+	/* How many metadata blocks are needed for addressing upper_limit? */
+	upper_limit -= EXT4_NDIR_BLOCKS;
 	/* indirect blocks */
 	meta_blocks = 1;
+	upper_limit -= ppb;
 	/* double indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2));
-	/* tripple indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
-
-	upper_limit -= meta_blocks;
-	upper_limit <<= bits;
-
-	res += 1LL << (bits-2);
-	res += 1LL << (2*(bits-2));
-	res += 1LL << (3*(bits-2));
+	if (upper_limit < ppb * ppb) {
+		meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb);
+		res -= meta_blocks;
+		goto check_lfs;
+	}
+	meta_blocks += 1 + ppb;
+	upper_limit -= ppb * ppb;
+	/* tripple indirect blocks for the rest */
+	meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) +
+		DIV_ROUND_UP_ULL(upper_limit, ppb*ppb);
+	res -= meta_blocks;
+check_lfs:
 	res <<= bits;
-	if (res > upper_limit)
-		res = upper_limit;
-
 	if (res > MAX_LFS_FILESIZE)
 		res = MAX_LFS_FILESIZE;
 
-	return (loff_t)res;
+	return res;
 }
 
 static ext4_fsblk_t descriptor_loc(struct super_block *sb,
@@ -4369,7 +4403,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 
 	/* Set defaults for the variables that will be set during parsing */
 	ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
-	ctx->mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN;
 
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sectors_written_start =
@@ -5320,12 +5353,12 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	 * turned off by passing "mb_optimize_scan=0". This can also be
 	 * turned on forcefully by passing "mb_optimize_scan=1".
 	 */
-	if (ctx->mb_optimize_scan == 1)
+	if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) {
+		if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
 			set_opt2(sb, MB_OPTIMIZE_SCAN);
-	else if (ctx->mb_optimize_scan == 0)
+		else
 			clear_opt2(sb, MB_OPTIMIZE_SCAN);
-	else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
-		set_opt2(sb, MB_OPTIMIZE_SCAN);
+	}
 
 	err = ext4_mb_init(sb);
 	if (err) {

fs/jbd2/transaction.c

@@ -107,7 +107,6 @@ static void jbd2_get_transaction(journal_t *journal,
 	transaction->t_start_time = ktime_get();
 	transaction->t_tid = journal->j_transaction_sequence++;
 	transaction->t_expires = jiffies + journal->j_commit_interval;
-	spin_lock_init(&transaction->t_handle_lock);
 	atomic_set(&transaction->t_updates, 0);
 	atomic_set(&transaction->t_outstanding_credits,
 		   jbd2_descriptor_blocks_per_trans(journal) +
@@ -139,26 +138,22 @@ static void jbd2_get_transaction(journal_t *journal,
 /*
  * Update transaction's maximum wait time, if debugging is enabled.
  *
- * In order for t_max_wait to be reliable, it must be protected by a
- * lock.  But doing so will mean that start_this_handle() can not be
- * run in parallel on SMP systems, which limits our scalability.  So
- * unless debugging is enabled, we no longer update t_max_wait, which
- * means that maximum wait time reported by the jbd2_run_stats
- * tracepoint will always be zero.
+ * t_max_wait is carefully updated here with use of atomic compare exchange.
+ * Note that there could be multiplre threads trying to do this simultaneously
+ * hence using cmpxchg to avoid any use of locks in this case.
+ * With this t_max_wait can be updated w/o enabling jbd2_journal_enable_debug.
  */
 static inline void update_t_max_wait(transaction_t *transaction,
 				     unsigned long ts)
 {
-#ifdef CONFIG_JBD2_DEBUG
-	if (jbd2_journal_enable_debug &&
-	    time_after(transaction->t_start, ts)) {
-		ts = jbd2_time_diff(ts, transaction->t_start);
-		spin_lock(&transaction->t_handle_lock);
-		if (ts > transaction->t_max_wait)
-			transaction->t_max_wait = ts;
-		spin_unlock(&transaction->t_handle_lock);
-	}
-#endif
+	unsigned long oldts, newts;
+
+	if (time_after(transaction->t_start, ts)) {
+		newts = jbd2_time_diff(ts, transaction->t_start);
+		oldts = READ_ONCE(transaction->t_max_wait);
+		while (oldts < newts)
+			oldts = cmpxchg(&transaction->t_max_wait, oldts, newts);
+	}
 }
 
 /*
@@ -690,7 +685,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
 		DIV_ROUND_UP(
 			handle->h_revoke_credits_requested,
 			journal->j_revoke_records_per_block);
-	spin_lock(&transaction->t_handle_lock);
 	wanted = atomic_add_return(nblocks,
 				   &transaction->t_outstanding_credits);
 
@@ -698,7 +692,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
 		jbd_debug(3, "denied handle %p %d blocks: "
 			  "transaction too large\n", handle, nblocks);
 		atomic_sub(nblocks, &transaction->t_outstanding_credits);
-		goto unlock;
+		goto error_out;
 	}
 
 	trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
@@ -714,8 +708,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
 	result = 0;
 
 	jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
-unlock:
-	spin_unlock(&transaction->t_handle_lock);
 error_out:
 	read_unlock(&journal->j_state_lock);
 	return result;
@@ -842,27 +834,35 @@ EXPORT_SYMBOL(jbd2_journal_restart);
  */
 void jbd2_journal_wait_updates(journal_t *journal)
 {
-	transaction_t *commit_transaction = journal->j_running_transaction;
+	DEFINE_WAIT(wait);
 
-	if (!commit_transaction)
-		return;
+	while (1) {
+		/*
+		 * Note that the running transaction can get freed under us if
+		 * this transaction is getting committed in
+		 * jbd2_journal_commit_transaction() ->
+		 * jbd2_journal_free_transaction(). This can only happen when we
+		 * release j_state_lock -> schedule() -> acquire j_state_lock.
+		 * Hence we should everytime retrieve new j_running_transaction
+		 * value (after j_state_lock release acquire cycle), else it may
+		 * lead to use-after-free of old freed transaction.
+		 */
+		transaction_t *transaction = journal->j_running_transaction;
 
-	spin_lock(&commit_transaction->t_handle_lock);
-	while (atomic_read(&commit_transaction->t_updates)) {
-		DEFINE_WAIT(wait);
+		if (!transaction)
+			break;
 
 		prepare_to_wait(&journal->j_wait_updates, &wait,
 				TASK_UNINTERRUPTIBLE);
-		if (atomic_read(&commit_transaction->t_updates)) {
-			spin_unlock(&commit_transaction->t_handle_lock);
+		if (!atomic_read(&transaction->t_updates)) {
+			finish_wait(&journal->j_wait_updates, &wait);
+			break;
+		}
 		write_unlock(&journal->j_state_lock);
 		schedule();
-			write_lock(&journal->j_state_lock);
-			spin_lock(&commit_transaction->t_handle_lock);
-		}
 		finish_wait(&journal->j_wait_updates, &wait);
+		write_lock(&journal->j_state_lock);
 	}
-	spin_unlock(&commit_transaction->t_handle_lock);
 }
 
 /**
@@ -877,8 +877,6 @@ void jbd2_journal_wait_updates(journal_t *journal)
  */
 void jbd2_journal_lock_updates(journal_t *journal)
 {
-	DEFINE_WAIT(wait);
-
 	jbd2_might_wait_for_commit(journal);
 
 	write_lock(&journal->j_state_lock);

include/linux/jbd2.h

@@ -554,9 +554,6 @@ struct transaction_chp_stats_s {
  *    ->j_list_lock
  *
  *    j_state_lock
- *    ->t_handle_lock
- *
- *    j_state_lock
  *    ->j_list_lock			(journal_unmap_buffer)
  *
  */

include/trace/events/ext4.h

@@ -95,6 +95,17 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_NOMEM);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_SWAP_BOOT);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA);
+TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX);
+
 #define show_fc_reason(reason)						\
 	__print_symbolic(reason,					\
 		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
@@ -2643,7 +2654,7 @@ TRACE_EVENT(ext4_fc_replay_scan,
 		__entry->off = off;
 	),
 
-	TP_printk("FC scan pass on dev %d,%d: error %d, off %d",
+	TP_printk("dev %d,%d error %d, off %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->error, __entry->off)
 );
@@ -2669,32 +2680,35 @@ TRACE_EVENT(ext4_fc_replay,
 		__entry->priv2 = priv2;
 	),
 
-	TP_printk("FC Replay %d,%d: tag %d, ino %d, data1 %d, data2 %d",
+	TP_printk("dev %d,%d: tag %d, ino %d, data1 %d, data2 %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->tag, __entry->ino, __entry->priv1, __entry->priv2)
 );
 
 TRACE_EVENT(ext4_fc_commit_start,
-	TP_PROTO(struct super_block *sb),
+	TP_PROTO(struct super_block *sb, tid_t commit_tid),
 
-	TP_ARGS(sb),
+	TP_ARGS(sb, commit_tid),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(tid_t, tid)
 	),
 
 	TP_fast_assign(
 		__entry->dev = sb->s_dev;
+		__entry->tid = commit_tid;
 	),
 
-	TP_printk("fast_commit started on dev %d,%d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev))
+	TP_printk("dev %d,%d tid %u", MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->tid)
 );
 
 TRACE_EVENT(ext4_fc_commit_stop,
-	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+	    TP_PROTO(struct super_block *sb, int nblks, int reason,
+		     tid_t commit_tid),
 
-	TP_ARGS(sb, nblks, reason),
+	TP_ARGS(sb, nblks, reason, commit_tid),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -2703,6 +2717,7 @@ TRACE_EVENT(ext4_fc_commit_stop,
 		__field(int, num_fc)
 		__field(int, num_fc_ineligible)
 		__field(int, nblks_agg)
+		__field(tid_t, tid)
 	),
 
 	TP_fast_assign(
@@ -2713,17 +2728,18 @@ TRACE_EVENT(ext4_fc_commit_stop,
 		__entry->num_fc_ineligible =
 			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
 		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+		__entry->tid = commit_tid;
 	),
 
-	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+	TP_printk("dev %d,%d nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d, tid %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->nblks, __entry->reason, __entry->num_fc,
-		  __entry->num_fc_ineligible, __entry->nblks_agg)
+		  __entry->num_fc_ineligible, __entry->nblks_agg, __entry->tid)
 );
 
 #define FC_REASON_NAME_STAT(reason)					\
 	show_fc_reason(reason),						\
-	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+	__entry->fc_ineligible_rc[reason]
 
 TRACE_EVENT(ext4_fc_stats,
 	TP_PROTO(struct super_block *sb),
@@ -2732,18 +2748,29 @@ TRACE_EVENT(ext4_fc_stats,
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		    __field(struct ext4_sb_info *, sbi)
-		    __field(int, count)
+		__array(unsigned int, fc_ineligible_rc, EXT4_FC_REASON_MAX)
+		__field(unsigned long, fc_commits)
+		__field(unsigned long, fc_ineligible_commits)
+		__field(unsigned long, fc_numblks)
 	),
 
 	TP_fast_assign(
+		int i;
+
 		__entry->dev = sb->s_dev;
-		    __entry->sbi = EXT4_SB(sb);
+		for (i = 0; i < EXT4_FC_REASON_MAX; i++) {
+			__entry->fc_ineligible_rc[i] =
+				EXT4_SB(sb)->s_fc_stats.fc_ineligible_reason_count[i];
+		}
+		__entry->fc_commits = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->fc_ineligible_commits =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->fc_numblks = EXT4_SB(sb)->s_fc_stats.fc_numblks;
 	),
 
-	    TP_printk("dev %d:%d fc ineligible reasons:\n"
-		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
-		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+	TP_printk("dev %d,%d fc ineligible reasons:\n"
+		  "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u "
+		  "num_commits:%lu, ineligible: %lu, numblks: %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
 		  FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
@@ -2754,87 +2781,140 @@ TRACE_EVENT(ext4_fc_stats,
 		  FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
 		  FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
 		  FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
-		      __entry->sbi->s_fc_stats.fc_num_commits,
-		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
-		      __entry->sbi->s_fc_stats.fc_numblks)
-
-);
-
-#define DEFINE_TRACE_DENTRY_EVENT(__type)				\
-	TRACE_EVENT(ext4_fc_track_##__type,				\
-	    TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \
-									\
-	    TP_ARGS(inode, dentry, ret),				\
-									\
-	    TP_STRUCT__entry(						\
-		    __field(dev_t, dev)					\
-		    __field(int, ino)					\
-		    __field(int, error)					\
-		    ),							\
-									\
-	    TP_fast_assign(						\
-		    __entry->dev = inode->i_sb->s_dev;			\
-		    __entry->ino = inode->i_ino;			\
-		    __entry->error = ret;				\
-		    ),							\
-									\
-	    TP_printk("dev %d:%d, inode %d, error %d, fc_%s",		\
-		      MAJOR(__entry->dev), MINOR(__entry->dev),		\
-		      __entry->ino, __entry->error,			\
-		      #__type)						\
+		  __entry->fc_commits, __entry->fc_ineligible_commits,
+		  __entry->fc_numblks)
+);
+
+DECLARE_EVENT_CLASS(ext4_fc_track_dentry,
+
+	TP_PROTO(handle_t *handle, struct inode *inode,
+		 struct dentry *dentry, int ret),
+
+	TP_ARGS(handle, inode, dentry, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(tid_t, t_tid)
+		__field(ino_t, i_ino)
+		__field(tid_t, i_sync_tid)
+		__field(int, error)
+	),
+
+	TP_fast_assign(
+		struct ext4_inode_info *ei = EXT4_I(inode);
+
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->t_tid = handle->h_transaction->t_tid;
+		__entry->i_ino = inode->i_ino;
+		__entry->i_sync_tid = ei->i_sync_tid;
+		__entry->error = ret;
+	),
+
+	TP_printk("dev %d,%d, t_tid %u, ino %lu, i_sync_tid %u, error %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->t_tid, __entry->i_ino, __entry->i_sync_tid,
+		  __entry->error
 	)
+);
 
-DEFINE_TRACE_DENTRY_EVENT(create);
-DEFINE_TRACE_DENTRY_EVENT(link);
-DEFINE_TRACE_DENTRY_EVENT(unlink);
+#define DEFINE_EVENT_CLASS_DENTRY(__type)				\
+DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type,		\
+	TP_PROTO(handle_t *handle, struct inode *inode,			\
+		 struct dentry *dentry, int ret),			\
+	TP_ARGS(handle, inode, dentry, ret)				\
+)
+
+DEFINE_EVENT_CLASS_DENTRY(create);
+DEFINE_EVENT_CLASS_DENTRY(link);
+DEFINE_EVENT_CLASS_DENTRY(unlink);
 
 TRACE_EVENT(ext4_fc_track_inode,
-	    TP_PROTO(struct inode *inode, int ret),
+	TP_PROTO(handle_t *handle, struct inode *inode, int ret),
 
-	    TP_ARGS(inode, ret),
+	TP_ARGS(handle, inode, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		    __field(int, ino)
+		__field(tid_t, t_tid)
+		__field(ino_t, i_ino)
+		__field(tid_t, i_sync_tid)
 		__field(int, error)
 	),
 
 	TP_fast_assign(
+		struct ext4_inode_info *ei = EXT4_I(inode);
+
 		__entry->dev = inode->i_sb->s_dev;
-		    __entry->ino = inode->i_ino;
+		__entry->t_tid = handle->h_transaction->t_tid;
+		__entry->i_ino = inode->i_ino;
+		__entry->i_sync_tid = ei->i_sync_tid;
 		__entry->error = ret;
 	),
 
-	    TP_printk("dev %d:%d, inode %d, error %d",
+	TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		      __entry->ino, __entry->error)
+		  __entry->t_tid, __entry->i_ino, __entry->i_sync_tid,
+		  __entry->error)
 	);
 
 TRACE_EVENT(ext4_fc_track_range,
-	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+	TP_PROTO(handle_t *handle, struct inode *inode,
+		 long start, long end, int ret),
 
-	    TP_ARGS(inode, start, end, ret),
+	TP_ARGS(handle, inode, start, end, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		    __field(int, ino)
+		__field(tid_t, t_tid)
+		__field(ino_t, i_ino)
+		__field(tid_t, i_sync_tid)
 		__field(long, start)
 		__field(long, end)
 		__field(int, error)
 	),
 
 	TP_fast_assign(
+		struct ext4_inode_info *ei = EXT4_I(inode);
+
 		__entry->dev = inode->i_sb->s_dev;
-		    __entry->ino = inode->i_ino;
+		__entry->t_tid = handle->h_transaction->t_tid;
+		__entry->i_ino = inode->i_ino;
+		__entry->i_sync_tid = ei->i_sync_tid;
 		__entry->start = start;
 		__entry->end = end;
 		__entry->error = ret;
 	),
 
-	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+	TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d, start %ld, end %ld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->t_tid, __entry->i_ino, __entry->i_sync_tid,
+		  __entry->error, __entry->start, __entry->end)
+	);
+
+TRACE_EVENT(ext4_fc_cleanup,
+	TP_PROTO(journal_t *journal, int full, tid_t tid),
+
+	TP_ARGS(journal, full, tid),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, j_fc_off)
+		__field(int, full)
+		__field(tid_t, tid)
+	),
+
+	TP_fast_assign(
+		struct super_block *sb = journal->j_private;
+
+		__entry->dev = sb->s_dev;
+		__entry->j_fc_off = journal->j_fc_off;
+		__entry->full = full;
+		__entry->tid = tid;
+	),
+
+	TP_printk("dev %d,%d, j_fc_off %d, full %d, tid %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		      __entry->ino, __entry->error, __entry->start,
-		      __entry->end)
+		  __entry->j_fc_off, __entry->full, __entry->tid)
 	);
 
 TRACE_EVENT(ext4_update_sb,