ext4: add discard/zeroout flags to journal flush

Add a flags argument to jbd2_journal_flush to enable discarding or
zero-filling the journal blocks while flushing the journal.

Signed-off-by: Leah Rumancik <leah.rumancik@gmail.com>
Link: https://lore.kernel.org/r/20210518151327.130198-1-leah.rumancik@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

6 files changed, 129 insertions, 16 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 211acfba3af7..e1ff4eb3ccba 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3223,7 +3223,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 		ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
 		journal = EXT4_JOURNAL(inode);
 		jbd2_journal_lock_updates(journal);
-		err = jbd2_journal_flush(journal);
+		err = jbd2_journal_flush(journal, 0);
 		jbd2_journal_unlock_updates(journal);
 
 		if (err)
@@ -6005,7 +6005,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	if (val)
 		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	else {
-		err = jbd2_journal_flush(journal);
+		err = jbd2_journal_flush(journal, 0);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
 			percpu_up_write(&sbi->s_writepages_rwsem);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a96d6721cef9..93e9419825b8 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -706,7 +706,7 @@ static long ext4_ioctl_group_add(struct file *file,
 	err = ext4_group_add(sb, input);
 	if (EXT4_SB(sb)->s_journal) {
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 	}
 	if (err == 0)
@@ -884,7 +884,7 @@ setversion_out:
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		}
 		if (err == 0)
@@ -1027,7 +1027,7 @@ mext_out:
 		if (EXT4_SB(sb)->s_journal) {
 			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		}
 		if (err == 0)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3b6203543607..ad3919dbd49e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5653,7 +5653,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
 		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	err = jbd2_journal_flush(journal);
+	err = jbd2_journal_flush(journal, 0);
 	if (err < 0)
 		goto out;
 
@@ -5795,7 +5795,7 @@ static int ext4_freeze(struct super_block *sb)
 		 * Don't clear the needs_recovery flag if we failed to
 		 * flush the journal.
 		 */
-		error = jbd2_journal_flush(journal);
+		error = jbd2_journal_flush(journal, 0);
 		if (error < 0)
 			goto out;
 
@@ -6389,7 +6389,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		 * otherwise be livelocked...
 		 */
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		if (err)
 			return err;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 2dc944442802..3a2ed60ea8b7 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1686,6 +1686,110 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 	write_unlock(&journal->j_state_lock);
 }
 
+/**
+ * __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock)
+ * @journal: The journal to erase.
+ * @flags: A discard/zeroout request is sent for each physically contigous
+ *	region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or
+ *	JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation
+ *	to perform.
+ *
+ * Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes
+ * will be explicitly written if no hardware offload is available, see
+ * blkdev_issue_zeroout for more details.
+ */
+static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
+{
+	int err = 0;
+	unsigned long block, log_offset; /* logical */
+	unsigned long long phys_block, block_start, block_stop; /* physical */
+	loff_t byte_start, byte_stop, byte_count;
+	struct request_queue *q = bdev_get_queue(journal->j_dev);
+
+	/* flags must be set to either discard or zeroout */
+	if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags ||
+			((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+			(flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
+		return -EINVAL;
+
+	if (!q)
+		return -ENXIO;
+
+	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	/*
+	 * lookup block mapping and issue discard/zeroout for each
+	 * contiguous region
+	 */
+	log_offset = be32_to_cpu(journal->j_superblock->s_first);
+	block_start =  ~0ULL;
+	for (block = log_offset; block < journal->j_total_len; block++) {
+		err = jbd2_journal_bmap(journal, block, &phys_block);
+		if (err) {
+			pr_err("JBD2: bad block at offset %lu", block);
+			return err;
+		}
+
+		if (block_start == ~0ULL) {
+			block_start = phys_block;
+			block_stop = block_start - 1;
+		}
+
+		/*
+		 * last block not contiguous with current block,
+		 * process last contiguous region and return to this block on
+		 * next loop
+		 */
+		if (phys_block != block_stop + 1) {
+			block--;
+		} else {
+			block_stop++;
+			/*
+			 * if this isn't the last block of journal,
+			 * no need to process now because next block may also
+			 * be part of this contiguous region
+			 */
+			if (block != journal->j_total_len - 1)
+				continue;
+		}
+
+		/*
+		 * end of contiguous region or this is last block of journal,
+		 * take care of the region
+		 */
+		byte_start = block_start * journal->j_blocksize;
+		byte_stop = block_stop * journal->j_blocksize;
+		byte_count = (block_stop - block_start + 1) *
+				journal->j_blocksize;
+
+		truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping,
+				byte_start, byte_stop);
+
+		if (flags & JBD2_JOURNAL_FLUSH_DISCARD) {
+			err = blkdev_issue_discard(journal->j_dev,
+					byte_start >> SECTOR_SHIFT,
+					byte_count >> SECTOR_SHIFT,
+					GFP_NOFS, 0);
+		} else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) {
+			err = blkdev_issue_zeroout(journal->j_dev,
+					byte_start >> SECTOR_SHIFT,
+					byte_count >> SECTOR_SHIFT,
+					GFP_NOFS, 0);
+		}
+
+		if (unlikely(err != 0)) {
+			pr_err("JBD2: (error %d) unable to wipe journal at physical blocks %llu - %llu",
+					err, block_start, block_stop);
+			return err;
+		}
+
+		/* reset start and stop after processing a region */
+		block_start = ~0ULL;
+	}
+
+	return blkdev_issue_flush(journal->j_dev);
+}
 
 /**
  * jbd2_journal_update_sb_errno() - Update error in the journal.
@@ -2246,13 +2350,18 @@ EXPORT_SYMBOL(jbd2_journal_clear_features);
 /**
  * jbd2_journal_flush() - Flush journal
  * @journal: Journal to act on.
+ * @flags: optional operation on the journal blocks after the flush (see below)
  *
  * Flush all data for a given journal to disk and empty the journal.
  * Filesystems can use this when remounting readonly to ensure that
- * recovery does not need to happen on remount.
+ * recovery does not need to happen on remount. Optionally, a discard or zeroout
+ * can be issued on the journal blocks after flushing.
+ *
+ * flags:
+ *	JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks
+ *	JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks
  */
-
-int jbd2_journal_flush(journal_t *journal)
+int jbd2_journal_flush(journal_t *journal, unsigned int flags)
 {
 	int err = 0;
 	transaction_t *transaction = NULL;
@@ -2306,6 +2415,10 @@ int jbd2_journal_flush(journal_t *journal)
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
 	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+
+	if (flags)
+		err = __jbd2_journal_erase(journal, flags);
+
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index e032f2e2c2c5..f1cc8258d34a 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6018,7 +6018,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	 * Then truncate log will be replayed resulting in cluster double free.
 	 */
 	jbd2_journal_lock_updates(journal->j_journal);
-	status = jbd2_journal_flush(journal->j_journal);
+	status = jbd2_journal_flush(journal->j_journal, 0);
 	jbd2_journal_unlock_updates(journal->j_journal);
 	if (status < 0) {
 		mlog_errno(status);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4e589ce2fce6..4f15750aac5d 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -308,7 +308,7 @@ static int ocfs2_commit_cache(struct ocfs2_super *osb)
 	}
 
 	jbd2_journal_lock_updates(journal->j_journal);
-	status = jbd2_journal_flush(journal->j_journal);
+	status = jbd2_journal_flush(journal->j_journal, 0);
 	jbd2_journal_unlock_updates(journal->j_journal);
 	if (status < 0) {
 		up_write(&journal->j_trans_barrier);
@@ -1000,7 +1000,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 	if (ocfs2_mount_local(osb)) {
 		jbd2_journal_lock_updates(journal->j_journal);
-		status = jbd2_journal_flush(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);
 		if (status < 0)
 			mlog_errno(status);
@@ -1070,7 +1070,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 
 	if (replayed) {
 		jbd2_journal_lock_updates(journal->j_journal);
-		status = jbd2_journal_flush(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);
 		if (status < 0)
 			mlog_errno(status);
@@ -1666,7 +1666,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 
 	/* wipe the journal */
 	jbd2_journal_lock_updates(journal);
-	status = jbd2_journal_flush(journal);
+	status = jbd2_journal_flush(journal, 0);
 	jbd2_journal_unlock_updates(journal);
 	if (status < 0)
 		mlog_errno(status);