Merge tag 'ext4_for_linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Many cleanups and bug fixes in ext4, especially for the fast commit
  feature.

  Also some performance improvements; in particular, improving IOPS and
  throughput on fast devices running Async Direct I/O by up to 20% by
  optimizing jbd2_transaction_committed()"

* tag 'ext4_for_linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits)
  ext4: make sure the first directory block is not a hole
  ext4: check dot and dotdot of dx_root before making dir indexed
  ext4: sanity check for NULL pointer after ext4_force_shutdown
  jbd2: increase maximum transaction size
  jbd2: drop pointless shrinker batch initialization
  jbd2: avoid infinite transaction commit loop
  jbd2: precompute number of transaction descriptor blocks
  jbd2: make jbd2_journal_get_max_txn_bufs() internal
  jbd2: avoid mount failed when commit block is partial submitted
  ext4: avoid writing unitialized memory to disk in EA inodes
  ext4: don't track ranges in fast_commit if inode has inlined data
  ext4: fix possible tid_t sequence overflows
  ext4: use ext4_update_inode_fsync_trans() helper in inode creation
  ext4: add missing MODULE_DESCRIPTION()
  jbd2: add missing MODULE_DESCRIPTION()
  ext4: use memtostr_pad() for s_volume_name
  jbd2: speed up jbd2_transaction_committed()
  ext4: make ext4_da_map_blocks() buffer_head unaware
  ext4: make ext4_insert_delayed_block() insert multi-blocks
  ext4: factor out a helper to check the cluster allocation state
  ...

1 files changed, 67 insertions, 56 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0d2825c131cc..1ebf2393bfb7 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -220,19 +220,12 @@ loop:
 		 * so we don't sleep
 		 */
 		DEFINE_WAIT(wait);
-		int should_sleep = 1;
 
 		prepare_to_wait(&journal->j_wait_commit, &wait,
 				TASK_INTERRUPTIBLE);
-		if (journal->j_commit_sequence != journal->j_commit_request)
-			should_sleep = 0;
 		transaction = journal->j_running_transaction;
-		if (transaction && time_after_eq(jiffies,
-						transaction->t_expires))
-			should_sleep = 0;
-		if (journal->j_flags & JBD2_UNMOUNT)
-			should_sleep = 0;
-		if (should_sleep) {
+		if (transaction == NULL ||
+		    time_before(jiffies, transaction->t_expires)) {
 			write_unlock(&journal->j_state_lock);
 			schedule();
 			write_lock(&journal->j_state_lock);
@@ -316,11 +309,8 @@ static void journal_kill_thread(journal_t *journal)
  *
  * Return value:
  *  <0: Error
- * >=0: Finished OK
- *
- * On success:
- * Bit 0 set == escape performed on the data
- * Bit 1 set == buffer copy-out performed (kfree the data after IO)
+ *  =0: Finished OK without escape
+ *  =1: Finished OK with escape
  */
 
 int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
@@ -328,7 +318,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 				  struct buffer_head **bh_out,
 				  sector_t blocknr)
 {
-	int need_copy_out = 0;
 	int done_copy_out = 0;
 	int do_escape = 0;
 	char *mapped_data;
@@ -355,7 +344,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	atomic_set(&new_bh->b_count, 1);
 
 	spin_lock(&jh_in->b_state_lock);
-repeat:
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
 	 * we use that version of the data for the commit.
@@ -365,8 +353,8 @@ repeat:
 		new_folio = virt_to_folio(jh_in->b_frozen_data);
 		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
 	} else {
-		new_folio = jh2bh(jh_in)->b_folio;
-		new_offset = offset_in_folio(new_folio, jh2bh(jh_in)->b_data);
+		new_folio = bh_in->b_folio;
+		new_offset = offset_in_folio(new_folio, bh_in->b_data);
 	}
 
 	mapped_data = kmap_local_folio(new_folio, new_offset);
@@ -383,54 +371,52 @@ repeat:
 	/*
 	 * Check for escaping
 	 */
-	if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER)) {
-		need_copy_out = 1;
+	if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER))
 		do_escape = 1;
-	}
 	kunmap_local(mapped_data);
 
 	/*
 	 * Do we need to do a data copy?
 	 */
-	if (need_copy_out && !done_copy_out) {
+	if (do_escape && !done_copy_out) {
 		char *tmp;
 
 		spin_unlock(&jh_in->b_state_lock);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
 		if (!tmp) {
 			brelse(new_bh);
+			free_buffer_head(new_bh);
 			return -ENOMEM;
 		}
 		spin_lock(&jh_in->b_state_lock);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
-			goto repeat;
+			goto copy_done;
 		}
 
 		jh_in->b_frozen_data = tmp;
 		memcpy_from_folio(tmp, new_folio, new_offset, bh_in->b_size);
-
-		new_folio = virt_to_folio(tmp);
-		new_offset = offset_in_folio(new_folio, tmp);
-		done_copy_out = 1;
-
 		/*
 		 * This isn't strictly necessary, as we're using frozen
 		 * data for the escaping, but it keeps consistency with
 		 * b_frozen_data usage.
 		 */
 		jh_in->b_frozen_triggers = jh_in->b_triggers;
+
+copy_done:
+		new_folio = virt_to_folio(jh_in->b_frozen_data);
+		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
+		done_copy_out = 1;
 	}
 
 	/*
 	 * Did we need to do an escaping?  Now we've done all the
 	 * copying, we can finally do so.
+	 * b_frozen_data is from jbd2_alloc() which always provides an
+	 * address from the direct kernels mapping.
 	 */
-	if (do_escape) {
-		mapped_data = kmap_local_folio(new_folio, new_offset);
-		*((unsigned int *)mapped_data) = 0;
-		kunmap_local(mapped_data);
-	}
+	if (do_escape)
+		*((unsigned int *)jh_in->b_frozen_data) = 0;
 
 	folio_set_bh(new_bh, new_folio, new_offset);
 	new_bh->b_size = bh_in->b_size;
@@ -454,7 +440,7 @@ repeat:
 	set_buffer_shadow(bh_in);
 	spin_unlock(&jh_in->b_state_lock);
 
-	return do_escape | (done_copy_out << 1);
+	return do_escape;
 }
 
 /*
@@ -789,17 +775,7 @@ 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)
 {
-	int ret = 1;
-
-	read_lock(&journal->j_state_lock);
-	if (journal->j_running_transaction &&
-	    journal->j_running_transaction->t_tid == tid)
-		ret = 0;
-	if (journal->j_committing_transaction &&
-	    journal->j_committing_transaction->t_tid == tid)
-		ret = 0;
-	read_unlock(&journal->j_state_lock);
-	return ret;
+	return tid_geq(READ_ONCE(journal->j_commit_sequence), tid);
 }
 EXPORT_SYMBOL(jbd2_transaction_committed);
 
@@ -1451,6 +1427,48 @@ static int journal_revoke_records_per_block(journal_t *journal)
 	return space / record_size;
 }
 
+static int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 3;
+}
+
+/*
+ * Base amount of descriptor blocks we reserve for each transaction.
+ */
+static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
+{
+	int tag_space = journal->j_blocksize - sizeof(journal_header_t);
+	int tags_per_block;
+
+	/* Subtract UUID */
+	tag_space -= 16;
+	if (jbd2_journal_has_csum_v2or3(journal))
+		tag_space -= sizeof(struct jbd2_journal_block_tail);
+	/* Commit code leaves a slack space of 16 bytes at the end of block */
+	tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
+	/*
+	 * Revoke descriptors are accounted separately so we need to reserve
+	 * space for commit block and normal transaction descriptor blocks.
+	 */
+	return 1 + DIV_ROUND_UP(jbd2_journal_get_max_txn_bufs(journal),
+				tags_per_block);
+}
+
+/*
+ * Initialize number of blocks each transaction reserves for its bookkeeping
+ * and maximum number of blocks a transaction can use. This needs to be called
+ * after the journal size and the fastcommit area size are initialized.
+ */
+static void jbd2_journal_init_transaction_limits(journal_t *journal)
+{
+	journal->j_revoke_records_per_block =
+				journal_revoke_records_per_block(journal);
+	journal->j_transaction_overhead_buffers =
+				jbd2_descriptor_blocks_per_trans(journal);
+	journal->j_max_transaction_buffers =
+				jbd2_journal_get_max_txn_bufs(journal);
+}
+
 /*
  * Load the on-disk journal superblock and read the key fields into the
  * journal_t.
@@ -1492,8 +1510,8 @@ static int journal_load_superblock(journal_t *journal)
 	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
-	journal->j_revoke_records_per_block =
-				journal_revoke_records_per_block(journal);
+	/* After journal features are set, we can compute transaction limits */
+	jbd2_journal_init_transaction_limits(journal);
 
 	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
@@ -1599,7 +1617,6 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 	journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan;
 	journal->j_shrinker->count_objects = jbd2_journal_shrink_count;
-	journal->j_shrinker->batch = journal->j_max_transaction_buffers;
 	journal->j_shrinker->private_data = journal;
 
 	shrinker_register(journal->j_shrinker);
@@ -1743,8 +1760,6 @@ static int journal_reset(journal_t *journal)
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;
 
-	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
-
 	/*
 	 * Now that journal recovery is done, turn fast commits off here. This
 	 * way, if fast commit was enabled before the crash but if now FS has
@@ -2285,8 +2300,6 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
 	journal->j_fc_first = journal->j_last + 1;
 	journal->j_fc_off = 0;
 	journal->j_free = journal->j_last - journal->j_first;
-	journal->j_max_transaction_buffers =
-		jbd2_journal_get_max_txn_bufs(journal);
 
 	return 0;
 }
@@ -2374,8 +2387,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
 	sb->s_feature_incompat  |= cpu_to_be32(incompat);
 	unlock_buffer(journal->j_sb_buffer);
-	journal->j_revoke_records_per_block =
-				journal_revoke_records_per_block(journal);
+	jbd2_journal_init_transaction_limits(journal);
 
 	return 1;
 #undef COMPAT_FEATURE_ON
@@ -2406,8 +2418,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
 	sb->s_feature_compat    &= ~cpu_to_be32(compat);
 	sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
 	sb->s_feature_incompat  &= ~cpu_to_be32(incompat);
-	journal->j_revoke_records_per_block =
-				journal_revoke_records_per_block(journal);
+	jbd2_journal_init_transaction_limits(journal);
 }
 EXPORT_SYMBOL(jbd2_journal_clear_features);