1 files changed, 62 insertions, 70 deletions

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4d1fda1f7143..dca4b5d8aaaa 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -63,28 +63,6 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
 }
 
 /*
- * 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(journal->j_max_transaction_buffers,
-				tags_per_block);
-}
-
-/*
  * jbd2_get_transaction: obtain a new transaction_t object.
  *
  * Simply initialise a new transaction. Initialize it in
@@ -109,12 +87,11 @@ static void jbd2_get_transaction(journal_t *journal,
 	transaction->t_expires = jiffies + journal->j_commit_interval;
 	atomic_set(&transaction->t_updates, 0);
 	atomic_set(&transaction->t_outstanding_credits,
-		   jbd2_descriptor_blocks_per_trans(journal) +
+		   journal->j_transaction_overhead_buffers +
 		   atomic_read(&journal->j_reserved_credits));
 	atomic_set(&transaction->t_outstanding_revokes, 0);
 	atomic_set(&transaction->t_handle_count, 0);
 	INIT_LIST_HEAD(&transaction->t_inode_list);
-	INIT_LIST_HEAD(&transaction->t_private_list);
 
 	/* Set up the commit timer for the new transaction. */
 	journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires);
@@ -136,12 +113,9 @@ static void jbd2_get_transaction(journal_t *journal,
  */
 
 /*
- * Update transaction's maximum wait time, if debugging is enabled.
- *
  * t_max_wait is carefully updated here with use of atomic compare exchange.
  * Note that there could be multiplre threads trying to do this simultaneously
  * hence using cmpxchg to avoid any use of locks in this case.
- * With this t_max_wait can be updated w/o enabling jbd2_journal_enable_debug.
  */
 static inline void update_t_max_wait(transaction_t *transaction,
 				     unsigned long ts)
@@ -213,6 +187,13 @@ static void sub_reserved_credits(journal_t *journal, int blocks)
 	wake_up(&journal->j_wait_reserved);
 }
 
+/* Maximum number of blocks for user transaction payload */
+static int jbd2_max_user_trans_buffers(journal_t *journal)
+{
+	return journal->j_max_transaction_buffers -
+				journal->j_transaction_overhead_buffers;
+}
+
 /*
  * Wait until we can add credits for handle to the running transaction.  Called
  * with j_state_lock held for reading. Returns 0 if handle joined the running
@@ -262,12 +243,12 @@ __must_hold(&journal->j_state_lock)
 		 * big to fit this handle? Wait until reserved credits are freed.
 		 */
 		if (atomic_read(&journal->j_reserved_credits) + total >
-		    journal->j_max_transaction_buffers) {
+		    jbd2_max_user_trans_buffers(journal)) {
 			read_unlock(&journal->j_state_lock);
 			jbd2_might_wait_for_commit(journal);
 			wait_event(journal->j_wait_reserved,
 				   atomic_read(&journal->j_reserved_credits) + total <=
-				   journal->j_max_transaction_buffers);
+				   jbd2_max_user_trans_buffers(journal));
 			__acquire(&journal->j_state_lock); /* fake out sparse */
 			return 1;
 		}
@@ -307,14 +288,14 @@ __must_hold(&journal->j_state_lock)
 
 	needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits);
 	/* We allow at most half of a transaction to be reserved */
-	if (needed > journal->j_max_transaction_buffers / 2) {
+	if (needed > jbd2_max_user_trans_buffers(journal) / 2) {
 		sub_reserved_credits(journal, rsv_blocks);
 		atomic_sub(total, &t->t_outstanding_credits);
 		read_unlock(&journal->j_state_lock);
 		jbd2_might_wait_for_commit(journal);
 		wait_event(journal->j_wait_reserved,
 			 atomic_read(&journal->j_reserved_credits) + rsv_blocks
-			 <= journal->j_max_transaction_buffers / 2);
+			 <= jbd2_max_user_trans_buffers(journal) / 2);
 		__acquire(&journal->j_state_lock); /* fake out sparse */
 		return 1;
 	}
@@ -344,12 +325,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 	 * size and limit the number of total credits to not exceed maximum
 	 * transaction size per operation.
 	 */
-	if ((rsv_blocks > journal->j_max_transaction_buffers / 2) ||
-	    (rsv_blocks + blocks > journal->j_max_transaction_buffers)) {
+	if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 ||
+	    rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) {
 		printk(KERN_ERR "JBD2: %s wants too many credits "
 		       "credits:%d rsv_credits:%d max:%d\n",
 		       current->comm, blocks, rsv_blocks,
-		       journal->j_max_transaction_buffers);
+		       jbd2_max_user_trans_buffers(journal));
 		WARN_ON(1);
 		return -ENOSPC;
 	}
@@ -460,7 +441,7 @@ repeat:
 	read_unlock(&journal->j_state_lock);
 	current->journal_info = handle;
 
-	rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
+	rwsem_acquire_read(&journal->j_trans_commit_map, 0, 1, _THIS_IP_);
 	jbd2_journal_free_transaction(new_transaction);
 	/*
 	 * Ensure that no allocations done while the transaction is open are
@@ -935,19 +916,15 @@ static void warn_dirty_buffer(struct buffer_head *bh)
 /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */
 static void jbd2_freeze_jh_data(struct journal_head *jh)
 {
-	struct page *page;
-	int offset;
 	char *source;
 	struct buffer_head *bh = jh2bh(jh);
 
 	J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n");
-	page = bh->b_page;
-	offset = offset_in_page(bh->b_data);
-	source = kmap_atomic(page);
+	source = kmap_local_folio(bh->b_folio, bh_offset(bh));
 	/* Fire data frozen trigger just before we copy the data */
-	jbd2_buffer_frozen_trigger(jh, source + offset, jh->b_triggers);
-	memcpy(jh->b_frozen_data, source + offset, bh->b_size);
-	kunmap_atomic(source);
+	jbd2_buffer_frozen_trigger(jh, source, jh->b_triggers);
+	memcpy(jh->b_frozen_data, source, bh->b_size);
+	kunmap_local(source);
 
 	/*
 	 * Now that the frozen data is saved off, we need to store any matching
@@ -1235,11 +1212,26 @@ out:
 int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
 {
 	struct journal_head *jh;
+	journal_t *journal;
 	int rc;
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
 
+	journal = handle->h_transaction->t_journal;
+	rc = jbd2_check_fs_dev_write_error(journal);
+	if (rc) {
+		/*
+		 * If the fs dev has writeback errors, it may have failed
+		 * to async write out metadata buffers in the background.
+		 * In this case, we could read old data from disk and write
+		 * it out again, which may lead to on-disk filesystem
+		 * inconsistency. Aborting journal can avoid it happen.
+		 */
+		jbd2_journal_abort(journal, rc);
+		return -EIO;
+	}
+
 	if (jbd2_write_access_granted(handle, bh, false))
 		return 0;
 
@@ -1293,14 +1285,23 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 	 * committing transaction's lists, but it HAS to be in Forget state in
 	 * that case: the transaction must have deleted the buffer for it to be
 	 * reused here.
+	 * In the case of file system data inconsistency, for example, if the
+	 * block bitmap of a referenced block is not set, it can lead to the
+	 * situation where a block being committed is allocated and used again.
+	 * As a result, the following condition will not be satisfied, so here
+	 * we directly trigger a JBD abort instead of immediately invoking
+	 * bugon.
 	 */
 	spin_lock(&jh->b_state_lock);
-	J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
-		jh->b_transaction == NULL ||
-		(jh->b_transaction == journal->j_committing_transaction &&
-			  jh->b_jlist == BJ_Forget)));
+	if (!(jh->b_transaction == transaction || jh->b_transaction == NULL ||
+	      (jh->b_transaction == journal->j_committing_transaction &&
+	       jh->b_jlist == BJ_Forget)) || jh->b_next_transaction != NULL) {
+		err = -EROFS;
+		spin_unlock(&jh->b_state_lock);
+		jbd2_journal_abort(journal, err);
+		goto out;
+	}
 
-	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
 	J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
 
 	if (jh->b_transaction == NULL) {
@@ -1518,7 +1519,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 				jh->b_next_transaction == transaction);
 		spin_unlock(&jh->b_state_lock);
 	}
-	if (jh->b_modified == 1) {
+	if (data_race(jh->b_modified == 1)) {
 		/* If it's in our transaction it must be in BJ_Metadata list. */
 		if (data_race(jh->b_transaction == transaction &&
 		    jh->b_jlist != BJ_Metadata)) {
@@ -1537,7 +1538,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		goto out;
 	}
 
-	journal = transaction->t_journal;
 	spin_lock(&jh->b_state_lock);
 
 	if (is_handle_aborted(handle)) {
@@ -1552,6 +1552,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		goto out_unlock_bh;
 	}
 
+	journal = transaction->t_journal;
+
 	if (jh->b_modified == 0) {
 		/*
 		 * This buffer's got modified and becoming part
@@ -1667,6 +1669,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 	int drop_reserve = 0;
 	int err = 0;
 	int was_modified = 0;
+	int wait_for_writeback = 0;
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
@@ -1790,18 +1793,22 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 		}
 
 		/*
-		 * The buffer is still not written to disk, we should
-		 * attach this buffer to current transaction so that the
-		 * buffer can be checkpointed only after the current
-		 * transaction commits.
+		 * The buffer has not yet been written to disk. We should
+		 * either clear the buffer or ensure that the ongoing I/O
+		 * is completed, and attach this buffer to current
+		 * transaction so that the buffer can be checkpointed only
+		 * after the current transaction commits.
 		 */
 		clear_buffer_dirty(bh);
+		wait_for_writeback = 1;
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
 		spin_unlock(&journal->j_list_lock);
 	}
 drop:
 	__brelse(bh);
 	spin_unlock(&jh->b_state_lock);
+	if (wait_for_writeback)
+		wait_on_buffer(bh);
 	jbd2_journal_put_journal_head(jh);
 	if (drop_reserve) {
 		/* no need to reserve log space for this block -bzzz */
@@ -2084,21 +2091,6 @@ static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 	jh->b_transaction = NULL;
 }
 
-void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
-{
-	struct buffer_head *bh = jh2bh(jh);
-
-	/* Get reference so that buffer cannot be freed before we unlock it */
-	get_bh(bh);
-	spin_lock(&jh->b_state_lock);
-	spin_lock(&journal->j_list_lock);
-	__jbd2_journal_unfile_buffer(jh);
-	spin_unlock(&journal->j_list_lock);
-	spin_unlock(&jh->b_state_lock);
-	jbd2_journal_put_journal_head(jh);
-	__brelse(bh);
-}
-
 /**
  * jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
@@ -2197,7 +2189,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 		/*
 		 * We don't want to write the buffer anymore, clear the
 		 * bit so that we don't confuse checks in
-		 * __journal_file_buffer
+		 * __jbd2_journal_file_buffer
 		 */
 		clear_buffer_dirty(bh);
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);