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

Pull ext4 updates from Ted Ts'o:
 "The siginificant new ext4 feature this time around is Harshad's new
  fast_commit mode.

  In addition, thanks to Mauricio for fixing a race where mmap'ed pages
  that are being changed in parallel with a data=journal transaction
  commit could result in bad checksums in the failure that could cause
  journal replays to fail.

  Also notable is Ritesh's buffered write optimization which can result
  in significant improvements on parallel write workloads. (The kernel
  test robot reported a 330.6% improvement on fio.write_iops on a 96
  core system using DAX)

  Besides that, we have the usual miscellaneous cleanups and bug fixes"

Link: https://lore.kernel.org/r/20200925071217.GO28663@shao2-debian

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
  ext4: fix invalid inode checksum
  ext4: add fast commit stats in procfs
  ext4: add a mount opt to forcefully turn fast commits on
  ext4: fast commit recovery path
  jbd2: fast commit recovery path
  ext4: main fast-commit commit path
  jbd2: add fast commit machinery
  ext4 / jbd2: add fast commit initialization
  ext4: add fast_commit feature and handling for extended mount options
  doc: update ext4 and journalling docs to include fast commit feature
  ext4: Detect already used quota file early
  jbd2: avoid transaction reuse after reformatting
  ext4: use the normal helper to get the actual inode
  ext4: fix bs < ps issue reported with dioread_nolock mount opt
  ext4: data=journal: write-protect pages on j_submit_inode_data_buffers()
  ext4: data=journal: fixes for ext4_page_mkwrite()
  jbd2, ext4, ocfs2: introduce/use journal callbacks j_submit|finish_inode_data_buffers()
  jbd2: introduce/export functions jbd2_journal_submit|finish_inode_data_buffers()
  ext4: introduce ext4_sb_bread_unmovable() to replace sb_bread_unmovable()
  ext4: use ext4_sb_bread() instead of sb_bread()
  ...

2 files changed, 344 insertions, 8 deletions

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 08f904943ab2..fb3d71ad6eea 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -289,6 +289,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
 #define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
+#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT	0x00000020
 
 /* See "journal feature predicate functions" below */
 
@@ -299,7 +300,8 @@ typedef struct journal_superblock_s
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
 					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V3)
+					JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
+					JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
 
 #ifdef __KERNEL__
 
@@ -452,8 +454,8 @@ struct jbd2_inode {
 struct jbd2_revoke_table_s;
 
 /**
- * struct handle_s - The handle_s type is the concrete type associated with
- *     handle_t.
+ * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete
+ *     type associated with handle_t.
  * @h_transaction: Which compound transaction is this update a part of?
  * @h_journal: Which journal handle belongs to - used iff h_reserved set.
  * @h_rsv_handle: Handle reserved for finishing the logical operation.
@@ -629,7 +631,9 @@ struct transaction_s
 	struct journal_head	*t_shadow_list;
 
 	/*
-	 * List of inodes whose data we've modified in data=ordered mode.
+	 * List of inodes associated with the transaction; e.g., ext4 uses
+	 * this to track inodes in data=ordered and data=journal mode that
+	 * need special handling on transaction commit; also used by ocfs2.
 	 * [j_list_lock]
 	 */
 	struct list_head	t_inode_list;
@@ -747,6 +751,11 @@ jbd2_time_diff(unsigned long start, unsigned long end)
 
 #define JBD2_NR_BATCH	64
 
+enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
+
+#define JBD2_FC_REPLAY_STOP	0
+#define JBD2_FC_REPLAY_CONTINUE	1
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -858,6 +867,13 @@ struct journal_s
 	wait_queue_head_t	j_wait_reserved;
 
 	/**
+	 * @j_fc_wait:
+	 *
+	 * Wait queue to wait for completion of async fast commits.
+	 */
+	wait_queue_head_t	j_fc_wait;
+
+	/**
 	 * @j_checkpoint_mutex:
 	 *
 	 * Semaphore for locking against concurrent checkpoints.
@@ -915,6 +931,30 @@ struct journal_s
 	unsigned long		j_last;
 
 	/**
+	 * @j_fc_first:
+	 *
+	 * The block number of the first fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_first;
+
+	/**
+	 * @j_fc_off:
+	 *
+	 * Number of fast commit blocks currently allocated.
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_off;
+
+	/**
+	 * @j_fc_last:
+	 *
+	 * The block number one beyond the last fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_last;
+
+	/**
 	 * @j_dev: Device where we store the journal.
 	 */
 	struct block_device	*j_dev;
@@ -1065,6 +1105,12 @@ struct journal_s
 	struct buffer_head	**j_wbuf;
 
 	/**
+	 * @j_fc_wbuf: Array of fast commit bhs for
+	 * jbd2_journal_commit_transaction.
+	 */
+	struct buffer_head	**j_fc_wbuf;
+
+	/**
 	 * @j_wbufsize:
 	 *
 	 * Size of @j_wbuf array.
@@ -1072,6 +1118,13 @@ struct journal_s
 	int			j_wbufsize;
 
 	/**
+	 * @j_fc_wbufsize:
+	 *
+	 * Size of @j_fc_wbuf array.
+	 */
+	int			j_fc_wbufsize;
+
+	/**
 	 * @j_last_sync_writer:
 	 *
 	 * The pid of the last person to run a synchronous operation
@@ -1111,6 +1164,27 @@ struct journal_s
 	void			(*j_commit_callback)(journal_t *,
 						     transaction_t *);
 
+	/**
+	 * @j_submit_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WRITE_DATA flag
+	 * before we start to write out the transaction to the journal.
+	 */
+	int			(*j_submit_inode_data_buffers)
+					(struct jbd2_inode *);
+
+	/**
+	 * @j_finish_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WAIT_DATA flag
+	 * after we have written the transaction to the journal
+	 * but before we write out the commit block.
+	 */
+	int			(*j_finish_inode_data_buffers)
+					(struct jbd2_inode *);
+
 	/*
 	 * Journal statistics
 	 */
@@ -1170,6 +1244,30 @@ struct journal_s
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+
+	/**
+	 * @j_fc_cleanup_callback:
+	 *
+	 * Clean-up after fast commit or full commit. JBD2 calls this function
+	 * after every commit operation.
+	 */
+	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
+
+	/*
+	 * @j_fc_replay_callback:
+	 *
+	 * File-system specific function that performs replay of a fast
+	 * commit. JBD2 calls this function for each fast commit block found in
+	 * the journal. This function should return JBD2_FC_REPLAY_CONTINUE
+	 * to indicate that the block was processed correctly and more fast
+	 * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP
+	 * indicates the end of replay (no more blocks remaining). A negative
+	 * return value indicates error.
+	 */
+	int (*j_fc_replay_callback)(struct journal_s *journal,
+				    struct buffer_head *bh,
+				    enum passtype pass, int off,
+				    tid_t expected_commit_id);
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1240,6 +1338,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(async_commit,	ASYNC_COMMIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
+JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
 /*
  * Journal flag definitions
@@ -1253,6 +1352,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
+#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
+#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1421,6 +1522,10 @@ extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
 extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
 			struct jbd2_inode *inode, loff_t start_byte,
 			loff_t length);
+extern int	   jbd2_journal_submit_inode_data_buffers(
+			struct jbd2_inode *jinode);
+extern int	   jbd2_journal_finish_inode_data_buffers(
+			struct jbd2_inode *jinode);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
@@ -1505,6 +1610,17 @@ void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
+/* Fast commit related APIs */
+int jbd2_fc_init(journal_t *journal, int num_fc_blks);
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit(journal_t *journal);
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_submit_inode_data(struct jbd2_inode *jinode);
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+int jbd2_fc_release_bufs(journal_t *journal);
+
 /*
  * is_journal_abort
  *
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 4c8b99ec8606..b14314fcf732 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -95,6 +95,16 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+#define show_fc_reason(reason)						\
+	__print_symbolic(reason,					\
+		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
+		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
+		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
+		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
+		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
+		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -1766,9 +1776,9 @@ TRACE_EVENT(ext4_ext_load_extent,
 );
 
 TRACE_EVENT(ext4_load_inode,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct super_block *sb, unsigned long ino),
 
-	TP_ARGS(inode),
+	TP_ARGS(sb, ino),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev		)
@@ -1776,8 +1786,8 @@ TRACE_EVENT(ext4_load_inode,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
-		__entry->ino		= inode->i_ino;
+		__entry->dev		= sb->s_dev;
+		__entry->ino		= ino;
 	),
 
 	TP_printk("dev %d,%d ino %ld",
@@ -2791,6 +2801,216 @@ TRACE_EVENT(ext4_lazy_itable_init,
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
+TRACE_EVENT(ext4_fc_replay_scan,
+	TP_PROTO(struct super_block *sb, int error, int off),
+
+	TP_ARGS(sb, error, off),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, error)
+		__field(int, off)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->error = error;
+		__entry->off = off;
+	),
+
+	TP_printk("FC scan pass on dev %d,%d: error %d, off %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->error, __entry->off)
+);
+
+TRACE_EVENT(ext4_fc_replay,
+	TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2),
+
+	TP_ARGS(sb, tag, ino, priv1, priv2),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, tag)
+		__field(int, ino)
+		__field(int, priv1)
+		__field(int, priv2)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->tag = tag;
+		__entry->ino = ino;
+		__entry->priv1 = priv1;
+		__entry->priv2 = priv2;
+	),
+
+	TP_printk("FC Replay %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_ARGS(sb),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+	),
+
+	TP_printk("fast_commit started on dev %d,%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+);
+
+TRACE_EVENT(ext4_fc_commit_stop,
+	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+
+	TP_ARGS(sb, nblks, reason),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, nblks)
+		__field(int, reason)
+		__field(int, num_fc)
+		__field(int, num_fc_ineligible)
+		__field(int, nblks_agg)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->nblks = nblks;
+		__entry->reason = reason;
+		__entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->num_fc_ineligible =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+	),
+
+	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nblks, __entry->reason, __entry->num_fc,
+		  __entry->num_fc_ineligible, __entry->nblks_agg)
+);
+
+#define FC_REASON_NAME_STAT(reason)					\
+	show_fc_reason(reason),						\
+	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+
+TRACE_EVENT(ext4_fc_stats,
+	    TP_PROTO(struct super_block *sb),
+
+	    TP_ARGS(sb),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(struct ext4_sb_info *, sbi)
+		    __field(int, count)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = sb->s_dev;
+		    __entry->sbi = EXT4_SB(sb);
+		    ),
+
+	    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; "
+		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      __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)						\
+	)
+
+DEFINE_TRACE_DENTRY_EVENT(create);
+DEFINE_TRACE_DENTRY_EVENT(link);
+DEFINE_TRACE_DENTRY_EVENT(unlink);
+
+TRACE_EVENT(ext4_fc_track_inode,
+	    TP_PROTO(struct inode *inode, int ret),
+
+	    TP_ARGS(inode, 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",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error)
+	);
+
+TRACE_EVENT(ext4_fc_track_range,
+	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+
+	    TP_ARGS(inode, start, end, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(long, start)
+		    __field(long, end)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->start = start;
+		    __entry->end = end;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error, __entry->start,
+		      __entry->end)
+	);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */