From 15a119e09344a346384ec05c781c126a29b18235 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Wed, 23 Sep 2020 01:12:31 +0800
Subject: jbd2: fix the comment of struct jbd2_journal_handle

the struct name was modified long ago, but the comment still
use struct handle_s.

Signed-off-by: Hui Su <sh_def@163.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20200922171231.GA53120@rlk
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/jbd2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 08f904943ab2..a1ef05412acf 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -452,8 +452,8 @@ 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.
-- 
cgit v1.2.3


From aa3c0c61f62d682259e3e66cdc01846290f9cd6c Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:38 -0300
Subject: jbd2: introduce/export functions
 jbd2_journal_submit|finish_inode_data_buffers()

Export functions that implement the current behavior done
for an inode in journal_submit|finish_inode_data_buffers().

No functional change.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-2-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/commit.c     | 36 ++++++++++++++++--------------------
 fs/jbd2/journal.c    |  2 ++
 include/linux/jbd2.h |  4 ++++
 3 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6d2da8ad0e6f..f79b86b4241f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -187,19 +187,17 @@ static int journal_wait_on_commit_record(journal_t *journal,
  * use writepages() because with delayed allocation we may be doing
  * block allocation in writepages().
  */
-static int journal_submit_inode_data_buffers(struct address_space *mapping,
-		loff_t dirty_start, loff_t dirty_end)
+int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 {
-	int ret;
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
 	struct writeback_control wbc = {
 		.sync_mode =  WB_SYNC_ALL,
 		.nr_to_write = mapping->nrpages * 2,
-		.range_start = dirty_start,
-		.range_end = dirty_end,
+		.range_start = jinode->i_dirty_start,
+		.range_end = jinode->i_dirty_end,
 	};
 
-	ret = generic_writepages(mapping, &wbc);
-	return ret;
+	return generic_writepages(mapping, &wbc);
 }
 
 /*
@@ -215,16 +213,11 @@ static int journal_submit_data_buffers(journal_t *journal,
 {
 	struct jbd2_inode *jinode;
 	int err, ret = 0;
-	struct address_space *mapping;
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WRITE_DATA))
 			continue;
-		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		/*
@@ -234,8 +227,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 		 * only allocated blocks here.
 		 */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = journal_submit_inode_data_buffers(mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_submit_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
@@ -248,6 +240,15 @@ static int journal_submit_data_buffers(journal_t *journal,
 	return ret;
 }
 
+int jbd2_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
+
+	return filemap_fdatawait_range_keep_errors(mapping,
+						   jinode->i_dirty_start,
+						   jinode->i_dirty_end);
+}
+
 /*
  * Wait for data submitted for writeout, refile inodes to proper
  * transaction if needed.
@@ -262,16 +263,11 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WAIT_DATA))
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait_range_keep_errors(
-				jinode->i_vfs_inode->i_mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_finish_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 17fdc482f554..c0600405e7a2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -91,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
+EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers);
+EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a1ef05412acf..8b7b06066bc2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1421,6 +1421,10 @@ 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);
-- 
cgit v1.2.3


From 342af94ec6c02aa478fe2adcd41b950e154b03ba Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:39 -0300
Subject: jbd2, ext4, ocfs2: introduce/use journal callbacks
 j_submit|finish_inode_data_buffers()

Introduce journal callbacks to allow different behaviors
for an inode in journal_submit|finish_inode_data_buffers().

The existing users of the current behavior (ext4, ocfs2)
are adapted to use the previously exported functions
that implement the current behavior.

Users are callers of jbd2_journal_inode_ranged_write|wait(),
which adds the inode to the transaction's inode list with
the JI_WRITE|WAIT_DATA flags. Only ext4 and ocfs2 in-tree.

Both CONFIG_EXT4_FS and CONFIG_OCSFS2_FS select CONFIG_JBD2,
which builds fs/jbd2/commit.c and journal.c that define and
export the functions, so we can call directly in ext4/ocfs2.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-3-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c      |  4 ++++
 fs/jbd2/commit.c     | 30 ++++++++++++++++++------------
 fs/ocfs2/journal.c   |  4 ++++
 include/linux/jbd2.h | 25 ++++++++++++++++++++++++-
 4 files changed, 50 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0ee673e8e261..a3e57f554f1b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4752,6 +4752,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+	sbi->s_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	sbi->s_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 
 no_journal:
 	if (!test_opt(sb, NO_MBCACHE)) {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f79b86b4241f..6252b4c50666 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -197,6 +197,12 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 		.range_end = jinode->i_dirty_end,
 	};
 
+	/*
+	 * submit the inode data buffers. We use writepage
+	 * instead of writepages. Because writepages can do
+	 * block allocation with delalloc. We need to write
+	 * only allocated blocks here.
+	 */
 	return generic_writepages(mapping, &wbc);
 }
 
@@ -220,16 +226,13 @@ static int journal_submit_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		/*
-		 * submit the inode data buffers. We use writepage
-		 * instead of writepages. Because writepages can do
-		 * block allocation  with delalloc. We need to write
-		 * only allocated blocks here.
-		 */
+		/* submit the inode data buffers. */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = jbd2_journal_submit_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		if (journal->j_submit_inode_data_buffers) {
+			err = journal->j_submit_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
@@ -267,9 +270,12 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = jbd2_journal_finish_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		/* wait for the inode data buffers writeout. */
+		if (journal->j_finish_inode_data_buffers) {
+			err = journal->j_finish_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b425f0b01dce..b9a9d69dde7e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -883,6 +883,10 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 		  OCFS2_JOURNAL_DIRTY_FL);
 
 	journal->j_journal = j_journal;
+	journal->j_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	journal->j_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 	journal->j_inode = inode;
 	journal->j_bh = bh;
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 8b7b06066bc2..04afa6dcd60d 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -629,7 +629,9 @@ 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;
@@ -1111,6 +1113,27 @@ 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
 	 */
-- 
cgit v1.2.3


From 995a3ed67fc8c0e3301a770016fb66f1bbf15ec8 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:54 -0700
Subject: ext4: add fast_commit feature and handling for extended mount options

We are running out of mount option bits. Add handling for using
s_mount_opt2. Add ext4 and jbd2 fast commit feature flag and also add
ability to turn off the fast commit feature in Ext4.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-3-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h       |  4 ++++
 fs/ext4/super.c      | 27 ++++++++++++++++++++++-----
 include/linux/jbd2.h |  5 ++++-
 3 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1879531a119f..02d7dc378505 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1213,6 +1213,8 @@ 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 |= \
@@ -1813,6 +1815,7 @@ 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
@@ -1915,6 +1918,7 @@ 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)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f997fc95cc31..66423c598b70 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1709,7 +1709,7 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps,
+	Opt_prefetch_block_bitmaps, Opt_no_fc,
 };
 
 static const match_table_t tokens = {
@@ -1796,6 +1796,7 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_no_fc, "no_fc"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
@@ -1922,6 +1923,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
 #define MOPT_SKIP	0x0800
+#define	MOPT_2		0x1000
 
 static const struct mount_opts {
 	int	token;
@@ -2022,6 +2024,8 @@ static const struct mount_opts {
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
+	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
+	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
 	{Opt_err, 0, 0}
 };
 
@@ -2398,10 +2402,17 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			WARN_ON(1);
 			return -1;
 		}
-		if (arg != 0)
-			sbi->s_mount_opt |= m->mount_opt;
-		else
-			sbi->s_mount_opt &= ~m->mount_opt;
+		if (m->flags & MOPT_2) {
+			if (arg != 0)
+				sbi->s_mount_opt2 |= m->mount_opt;
+			else
+				sbi->s_mount_opt2 &= ~m->mount_opt;
+		} else {
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
+			else
+				sbi->s_mount_opt &= ~m->mount_opt;
+		}
 	}
 	return 1;
 }
@@ -2618,6 +2629,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("dax=inode");
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT))
+		SEQ_OPTS_PUTS("fast_commit");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -4121,6 +4135,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	if (ext4_has_feature_fast_commit(sb))
+		set_opt2(sb, JOURNAL_FAST_COMMIT);
 	/* don't forget to enable journal_csum when metadata_csum is enabled. */
 	if (ext4_has_metadata_csum(sb))
 		set_opt(sb, JOURNAL_CHECKSUM);
@@ -4777,6 +4793,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 04afa6dcd60d..0685cc95e501 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__
 
@@ -1263,6 +1265,7 @@ 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
-- 
cgit v1.2.3


From 6866d7b3f2bb4f011041ba54c98b1584497fe2fd Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:55 -0700
Subject: ext4 / jbd2: add fast commit initialization

This patch adds fast commit area trackers in the journal_t
structure. These are initialized via the jbd2_fc_init() routine that
this patch adds. This patch also adds ext4/fast_commit.c and
ext4/fast_commit.h files for fast commit code that will be added in
subsequent patches in this series.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-4-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/Makefile      |  2 +-
 fs/ext4/ext4.h        |  4 ++++
 fs/ext4/fast_commit.c | 20 +++++++++++++++++++
 fs/ext4/fast_commit.h |  9 +++++++++
 fs/ext4/super.c       |  1 +
 fs/jbd2/journal.c     | 53 ++++++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/jbd2.h  | 39 +++++++++++++++++++++++++++++++++++++
 7 files changed, 122 insertions(+), 6 deletions(-)
 create mode 100644 fs/ext4/fast_commit.c
 create mode 100644 fs/ext4/fast_commit.h

(limited to 'include/linux')

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 2e42f47a7f98..49e7af6cc93f 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -10,7 +10,7 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
 		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
-		xattr_user.o
+		xattr_user.o fast_commit.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 02d7dc378505..2c412d32db0f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -963,6 +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.
@@ -2678,6 +2679,9 @@ 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 */
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal);
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
new file mode 100644
index 000000000000..0dad8bdb1253
--- /dev/null
+++ b/fs/ext4/fast_commit.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * fs/ext4/fast_commit.c
+ *
+ * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com>
+ *
+ * Ext4 fast commits routines.
+ */
+#include "ext4_jbd2.h"
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal)
+{
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
+		return;
+	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
+		pr_warn("Error while enabling fast commits, turning off.");
+		ext4_clear_feature_fast_commit(sb);
+	}
+}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
new file mode 100644
index 000000000000..8362bf5e6e00
--- /dev/null
+++ b/fs/ext4/fast_commit.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __FAST_COMMIT_H__
+#define __FAST_COMMIT_H__
+
+/* Number of blocks in journal area to allocate for fast commits */
+#define EXT4_NUM_FC_BLKS		256
+
+#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66423c598b70..41da649ccaea 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5170,6 +5170,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
 	journal->j_commit_interval = sbi->s_commit_interval;
 	journal->j_min_batch_time = sbi->s_min_batch_time;
 	journal->j_max_batch_time = sbi->s_max_batch_time;
+	ext4_fc_init(sb, journal);
 
 	write_lock(&journal->j_state_lock);
 	if (test_opt(sb, BARRIER))
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c0600405e7a2..4497bfbac527 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1181,6 +1181,14 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	if (!journal->j_wbuf)
 		goto err_cleanup;
 
+	if (journal->j_fc_wbufsize > 0) {
+		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+					sizeof(struct buffer_head *),
+					GFP_KERNEL);
+		if (!journal->j_fc_wbuf)
+			goto err_cleanup;
+	}
+
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1194,11 +1202,23 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 err_cleanup:
 	kfree(journal->j_wbuf);
+	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }
 
+int jbd2_fc_init(journal_t *journal, int num_fc_blks)
+{
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_init);
+
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
  *
  * Create a journal structure assigned some fixed set of disk blocks to
@@ -1316,11 +1336,20 @@ static int journal_reset(journal_t *journal)
 	}
 
 	journal->j_first = first;
-	journal->j_last = last;
 
-	journal->j_head = first;
-	journal->j_tail = first;
-	journal->j_free = last - first;
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = last;
+		journal->j_last = last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = last;
+	}
+
+	journal->j_head = journal->j_first;
+	journal->j_tail = journal->j_first;
+	journal->j_free = journal->j_last - journal->j_first;
 
 	journal->j_tail_sequence = journal->j_transaction_sequence;
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
@@ -1665,9 +1694,18 @@ static int load_superblock(journal_t *journal)
 	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
-	journal->j_last = be32_to_cpu(sb->s_maxlen);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
 
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
+		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = be32_to_cpu(sb->s_maxlen);
+	}
+
 	return 0;
 }
 
@@ -1728,6 +1766,9 @@ int jbd2_journal_load(journal_t *journal)
 	 */
 	journal->j_flags &= ~JBD2_ABORT;
 
+	if (journal->j_fc_wbufsize > 0)
+		jbd2_journal_set_features(journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@@ -1811,6 +1852,8 @@ int jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
+	if (journal->j_fc_wbufsize > 0)
+		kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0685cc95e501..008629b4d615 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,6 +918,30 @@ 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.
 	 */
@@ -1068,6 +1092,12 @@ 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:
 	 *
@@ -1075,6 +1105,13 @@ struct journal_s
 	 */
 	int			j_wbufsize;
 
+	/**
+	 * @j_fc_wbufsize:
+	 *
+	 * Size of @j_fc_wbuf array.
+	 */
+	int			j_fc_wbufsize;
+
 	/**
 	 * @j_last_sync_writer:
 	 *
@@ -1535,6 +1572,8 @@ 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);
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From ff780b91efe901b8eecd8114785abae5341820ad Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:56 -0700
Subject: jbd2: add fast commit machinery

This functions adds necessary APIs needed in JBD2 layer for fast
commits.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-5-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c |   8 +++
 fs/jbd2/commit.c      |  44 ++++++++++++
 fs/jbd2/journal.c     | 190 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/jbd2.h  |  27 +++++++
 4 files changed, 268 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 0dad8bdb1253..f2d11b4c6b62 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -8,11 +8,19 @@
  * Ext4 fast commits routines.
  */
 #include "ext4_jbd2.h"
+/*
+ * Fast commit cleanup routine. This is called after every fast commit and
+ * full commit. full is true if we are called after a full commit.
+ */
+static void ext4_fc_cleanup(journal_t *journal, int full)
+{
+}
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
+	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
 	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
 		pr_warn("Error while enabling fast commits, turning off.");
 		ext4_clear_feature_fast_commit(sb);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6252b4c50666..fa688e163a80 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -206,6 +206,30 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 	return generic_writepages(mapping, &wbc);
 }
 
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return jbd2_journal_submit_inode_data_buffers(jinode);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
+}
+EXPORT_SYMBOL(jbd2_wait_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
@@ -415,6 +439,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -422,6 +460,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -1121,12 +1160,16 @@ restart_loop:
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1138,6 +1181,7 @@ restart_loop:
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 4497bfbac527..0c7c42bd530f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -159,7 +159,9 @@ static void commit_timeout(struct timer_list *t)
  *
  * 1) COMMIT:  Every so often we need to commit the current state of the
  *    filesystem to disk.  The journal thread is responsible for writing
- *    all of the metadata buffers to disk.
+ *    all of the metadata buffers to disk. If a fast commit is ongoing
+ *    journal thread waits until it's done and then continues from
+ *    there on.
  *
  * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
  *    of the data in that part of the log has been rewritten elsewhere on
@@ -716,6 +718,75 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return err;
 }
 
+/*
+ * Start a fast commit. If there's an ongoing fast or full commit wait for
+ * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
+ * if a fast commit is not needed, either because there's an already a commit
+ * going on or this tid has already been committed. Returns -EINVAL if no jbd2
+ * commit has yet been performed.
+ */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
+{
+	/*
+	 * Fast commits only allowed if at least one full commit has
+	 * been processed.
+	 */
+	if (!journal->j_stats.ts_tid)
+		return -EINVAL;
+
+	if (tid <= journal->j_commit_sequence)
+		return -EALREADY;
+
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_fc_wait, &wait);
+		return -EALREADY;
+	}
+	journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_begin_commit);
+
+/*
+ * Stop a fast commit. If fallback is set, this function starts commit of
+ * TID tid before any other fast commit can start.
+ */
+static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
+{
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 0);
+	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
+	if (fallback)
+		journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_fc_wait);
+	if (fallback)
+		return jbd2_complete_transaction(journal, tid);
+	return 0;
+}
+
+int jbd2_fc_end_commit(journal_t *journal)
+{
+	return __jbd2_fc_end_commit(journal, 0, 0);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit);
+
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+{
+	return __jbd2_fc_end_commit(journal, tid, 1);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
+
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
@@ -784,6 +855,110 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+/* Map one fast commit buffer for use by the file system */
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
+{
+	unsigned long long pblock;
+	unsigned long blocknr;
+	int ret = 0;
+	struct buffer_head *bh;
+	int fc_off;
+
+	*bh_out = NULL;
+	write_lock(&journal->j_state_lock);
+
+	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_fc_first + fc_off;
+		journal->j_fc_off++;
+	} else {
+		ret = -EINVAL;
+	}
+	write_unlock(&journal->j_state_lock);
+
+	if (ret)
+		return ret;
+
+	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
+	if (ret)
+		return ret;
+
+	bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
+	if (!bh)
+		return -ENOMEM;
+
+	lock_buffer(bh);
+
+	clear_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_get_buf);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
+		bh = journal->j_fc_wbuf[i];
+		wait_on_buffer(bh);
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_wait_bufs);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_release_bufs(journal_t *journal)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= 0; i--) {
+		bh = journal->j_fc_wbuf[i];
+		if (!bh)
+			break;
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_release_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
@@ -1142,6 +1317,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	init_waitqueue_head(&journal->j_fc_wait);
 	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
@@ -1495,6 +1671,7 @@ out:
 static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	bool had_fast_commit = false;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	lock_buffer(journal->j_sb_buffer);
@@ -1508,9 +1685,20 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
+	if (jbd2_has_feature_fast_commit(journal)) {
+		/*
+		 * When journal is clean, no need to commit fast commit flag and
+		 * make file system incompatible with older kernels.
+		 */
+		jbd2_clear_feature_fast_commit(journal);
+		had_fast_commit = true;
+	}
 
 	jbd2_write_superblock(journal, write_op);
 
+	if (had_fast_commit)
+		jbd2_set_feature_fast_commit(journal);
+
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 008629b4d615..a009d9b9c620 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -861,6 +861,13 @@ 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:
 	 *
@@ -1232,6 +1239,15 @@ 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);
+
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1316,6 +1332,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #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
@@ -1574,6 +1592,15 @@ 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
  *
-- 
cgit v1.2.3


From 5b849b5f96b47d82b5a432d8b91a8ad260e1de46 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:58 -0700
Subject: jbd2: fast commit recovery path

This patch adds fast commit recovery support in JBD2.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-7-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c | 15 ++++++++++++++
 fs/jbd2/recovery.c    | 57 +++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/jbd2.h  | 20 ++++++++++++++++++
 3 files changed, 88 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 79e947c43198..888d9d217d5b 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1188,8 +1188,23 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	trace_ext4_fc_stats(sb);
 }
 
+/*
+ * Main recovery path entry point.
+ */
+static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
+				enum passtype pass, int off, tid_t expected_tid)
+{
+	return 0;
+}
+
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
+	/*
+	 * We set replay callback even if fast commit disabled because we may
+	 * could still have fast commit blocks that need to be replayed even if
+	 * fast commit has now been turned off.
+	 */
+	journal->j_fc_replay_callback = ext4_fc_replay;
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index fb134c7a12c8..eb2606133cd8 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -35,7 +35,6 @@ struct recovery_info
 	int		nr_revoke_hits;
 };
 
-enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
 static int do_one_pass(journal_t *journal,
 				struct recovery_info *info, enum passtype pass);
 static int scan_revoke_records(journal_t *, struct buffer_head *,
@@ -225,10 +224,51 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 /* Make sure we wrap around the log correctly! */
 #define wrap(journal, var)						\
 do {									\
-	if (var >= (journal)->j_last)					\
-		var -= ((journal)->j_last - (journal)->j_first);	\
+	unsigned long _wrap_last =					\
+		jbd2_has_feature_fast_commit(journal) ?			\
+			(journal)->j_fc_last : (journal)->j_last;	\
+									\
+	if (var >= _wrap_last)						\
+		var -= (_wrap_last - (journal)->j_first);		\
 } while (0)
 
+static int fc_do_one_pass(journal_t *journal,
+			  struct recovery_info *info, enum passtype pass)
+{
+	unsigned int expected_commit_id = info->end_transaction;
+	unsigned long next_fc_block;
+	struct buffer_head *bh;
+	int err = 0;
+
+	next_fc_block = journal->j_fc_first;
+	if (!journal->j_fc_replay_callback)
+		return 0;
+
+	while (next_fc_block <= journal->j_fc_last) {
+		jbd_debug(3, "Fast commit replay: next block %ld",
+			  next_fc_block);
+		err = jread(&bh, journal, next_fc_block);
+		if (err) {
+			jbd_debug(3, "Fast commit replay: read error");
+			break;
+		}
+
+		jbd_debug(3, "Processing fast commit blk with seq %d");
+		err = journal->j_fc_replay_callback(journal, bh, pass,
+					next_fc_block - journal->j_fc_first,
+					expected_commit_id);
+		next_fc_block++;
+		if (err < 0 || err == JBD2_FC_REPLAY_STOP)
+			break;
+		err = 0;
+	}
+
+	if (err)
+		jbd_debug(3, "Fast commit replay failed, err = %d\n", err);
+
+	return err;
+}
+
 /**
  * jbd2_journal_recover - recovers a on-disk journal
  * @journal: the journal to recover
@@ -472,7 +512,9 @@ static int do_one_pass(journal_t *journal,
 				break;
 
 		jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
-			  next_commit_ID, next_log_block, journal->j_last);
+			  next_commit_ID, next_log_block,
+			  jbd2_has_feature_fast_commit(journal) ?
+			  journal->j_fc_last : journal->j_last);
 
 		/* Skip over each chunk of the transaction looking
 		 * either the next descriptor block or the final commit
@@ -834,6 +876,13 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
+
+	if (jbd2_has_feature_fast_commit(journal) &&  pass != PASS_REVOKE) {
+		err = fc_do_one_pass(journal, info, pass);
+		if (err)
+			success = err;
+	}
+
 	if (block_error && success == 0)
 		success = -EIO;
 	return success;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a009d9b9c620..fb3d71ad6eea 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -751,6 +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.
@@ -1248,6 +1253,21 @@ struct journal_s
 	 */
 	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) \
-- 
cgit v1.2.3