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()
  ...

1 files changed, 126 insertions, 10 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f9a692c0a66c..254d1c26bea8 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -27,7 +27,6 @@
 #include <linux/seqlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
-#include <linux/version.h>
 #include <linux/wait.h>
 #include <linux/sched/signal.h>
 #include <linux/blockgroup_lock.h>
@@ -492,7 +491,7 @@ struct flex_groups {
 
 /* Flags which are mutually exclusive to DAX */
 #define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
-			   EXT4_JOURNAL_DATA_FL)
+			   EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL)
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
@@ -964,6 +963,7 @@ do {									       \
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
 #include "extents_status.h"
+#include "fast_commit.h"
 
 /*
  * Lock subclasses for i_data_sem in the ext4_inode_info structure.
@@ -1021,6 +1021,31 @@ struct ext4_inode_info {
 
 	struct list_head i_orphan;	/* unlinked but open inodes */
 
+	/* Fast commit related info */
+
+	struct list_head i_fc_list;	/*
+					 * inodes that need fast commit
+					 * protected by sbi->s_fc_lock.
+					 */
+
+	/* Fast commit subtid when this inode was committed */
+	unsigned int i_fc_committed_subtid;
+
+	/* Start of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_start;
+
+	/* End of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_len;
+
+	/* Number of ongoing updates on this inode */
+	atomic_t  i_fc_updates;
+
+	/* Fast commit wait queue for this inode */
+	wait_queue_head_t i_fc_wait;
+
+	/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
+	struct mutex i_fc_lock;
+
 	/*
 	 * i_disksize keeps track of what the inode size is ON DISK, not
 	 * in memory.  During truncate, i_size is set to the new size by
@@ -1141,6 +1166,11 @@ struct ext4_inode_info {
 #define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT4_ERROR_FS			0x0002	/* Errors detected */
 #define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
+#define EXT4_FC_INELIGIBLE		0x0008	/* Fast commit ineligible */
+#define EXT4_FC_COMMITTING		0x0010	/* File system underoing a fast
+						 * commit.
+						 */
+#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
 
 /*
  * Misc. filesystem flags
@@ -1214,6 +1244,8 @@ struct ext4_inode_info {
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
+#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
 #define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
@@ -1481,14 +1513,14 @@ struct ext4_sb_info {
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
-	struct block_device *journal_bdev;
+	struct block_device *s_journal_bdev;
 #ifdef CONFIG_QUOTA
 	/* Names of quota files with journalled quota */
 	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
 	int s_jquota_fmt;			/* Format of quota to use */
 #endif
 	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
-	struct ext4_system_blocks __rcu *system_blks;
+	struct ext4_system_blocks __rcu *s_system_blks;
 
 #ifdef EXTENTS_STATS
 	/* ext4 extents stats */
@@ -1611,6 +1643,34 @@ struct ext4_sb_info {
 	/* Record the errseq of the backing block device */
 	errseq_t s_bdev_wb_err;
 	spinlock_t s_bdev_wb_lock;
+
+	/* Ext4 fast commit stuff */
+	atomic_t s_fc_subtid;
+	atomic_t s_fc_ineligible_updates;
+	/*
+	 * After commit starts, the main queue gets locked, and the further
+	 * updates get added in the staging queue.
+	 */
+#define FC_Q_MAIN	0
+#define FC_Q_STAGING	1
+	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
+					 * that have data changes in them.
+					 */
+	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
+	unsigned int s_fc_bytes;
+	/*
+	 * Main fast commit lock. This lock protects accesses to the
+	 * following fields:
+	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
+	 */
+	spinlock_t s_fc_lock;
+	struct buffer_head *s_fc_bh;
+	struct ext4_fc_stats s_fc_stats;
+	u64 s_fc_avg_commit_time;
+#ifdef CONFIG_EXT4_DEBUG
+	int s_fc_debug_max_replay;
+#endif
+	struct ext4_fc_replay_state s_fc_replay_state;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1721,6 +1781,7 @@ enum {
 	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
 	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
 	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -1814,6 +1875,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 #define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
@@ -1916,6 +1978,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
 EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
 EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
 EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
 EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
 
 EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
@@ -2650,6 +2713,7 @@ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 			  struct dx_hash_info *hinfo);
 
 /* ialloc.c */
+extern int ext4_mark_inode_used(struct super_block *sb, int ino);
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
 				      const struct qstr *qstr, __u32 goal,
 				      uid_t *owner, __u32 i_flags,
@@ -2675,6 +2739,27 @@ extern int ext4_init_inode_table(struct super_block *sb,
 				 ext4_group_t group, int barrier);
 extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
+/* fast_commit.c */
+int ext4_fc_info_show(struct seq_file *seq, void *v);
+void ext4_fc_init(struct super_block *sb, journal_t *journal);
+void ext4_fc_init_inode(struct inode *inode);
+void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end);
+void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_inode(struct inode *inode);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_start_ineligible(struct super_block *sb, int reason);
+void ext4_fc_stop_ineligible(struct super_block *sb);
+void ext4_fc_start_update(struct inode *inode);
+void ext4_fc_stop_update(struct inode *inode);
+void ext4_fc_del(struct inode *inode);
+bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
+void ext4_fc_replay_cleanup(struct super_block *sb);
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
+int __init ext4_fc_init_dentry_cache(void);
+
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
@@ -2704,8 +2789,12 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
+extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+		       int len, int state);
 
 /* inode.c */
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
@@ -2752,6 +2841,8 @@ extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
@@ -2785,12 +2876,15 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
+extern void ext4_reset_inode_seed(struct inode *inode);
 
 /* migrate.c */
 extern int ext4_ext_migrate(struct inode *);
 extern int ext4_ind_migrate(struct inode *inode);
 
 /* namei.c */
+extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
+			     struct inode *inode);
 extern int ext4_dirblock_csum_verify(struct inode *inode,
 				     struct buffer_head *bh);
 extern int ext4_orphan_add(handle_t *, struct inode *);
@@ -2824,6 +2918,14 @@ extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 /* super.c */
 extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 					 sector_t block, int op_flags);
+extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
+						   sector_t block);
+extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+				bh_end_io_t *end_io);
+extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
+			bh_end_io_t *end_io);
+extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
+extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
 extern int ext4_calculate_overhead(struct super_block *sb);
 extern void ext4_superblock_csum_set(struct super_block *sb);
@@ -3012,22 +3114,24 @@ static inline int ext4_has_group_desc_csum(struct super_block *sb)
 	return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
 }
 
+#define ext4_read_incompat_64bit_val(es, name) \
+	(((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \
+		? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \
+		le32_to_cpu(es->name##_lo))
+
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
-	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
-		le32_to_cpu(es->s_blocks_count_lo);
+	return ext4_read_incompat_64bit_val(es, s_blocks_count);
 }
 
 static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
 {
-	return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
-		le32_to_cpu(es->s_r_blocks_count_lo);
+	return ext4_read_incompat_64bit_val(es, s_r_blocks_count);
 }
 
 static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
 {
-	return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
-		le32_to_cpu(es->s_free_blocks_count_lo);
+	return ext4_read_incompat_64bit_val(es, s_free_blocks_count);
 }
 
 static inline void ext4_blocks_count_set(struct ext4_super_block *es,
@@ -3153,6 +3257,9 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 
 struct ext4_group_info {
 	unsigned long   bb_state;
+#ifdef AGGRESSIVE_CHECK
+	unsigned long	bb_check_counter;
+#endif
 	struct rb_root  bb_free_root;
 	ext4_grpblk_t	bb_first_free;	/* first free block */
 	ext4_grpblk_t	bb_free;	/* total free blocks */
@@ -3357,6 +3464,10 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
 extern int ext4_ci_compare(const struct inode *parent,
 			   const struct qstr *fname,
 			   const struct qstr *entry, bool quick);
+extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+			 struct inode *inode);
+extern int __ext4_link(struct inode *dir, struct inode *inode,
+		       struct dentry *dentry);
 
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
@@ -3457,6 +3568,11 @@ extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
 extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
 				       int check_cred, int restart_cred,
 				       int revoke_cred);
+extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
+extern int ext4_ext_replay_set_iblocks(struct inode *inode);
+extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+		int len, int unwritten, ext4_fsblk_t pblk);
+extern int ext4_ext_clear_bb(struct inode *inode);
 
 
 /* move_extent.c */