1 files changed, 94 insertions, 183 deletions

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 51bd38da21cd..9ec91017a7f3 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -27,7 +27,7 @@
  *
  * Called with j_list_lock held.
  */
-static inline void __buffer_unlink_first(struct journal_head *jh)
+static inline void __buffer_unlink(struct journal_head *jh)
 {
 	transaction_t *transaction = jh->b_cp_transaction;
 
@@ -41,45 +41,6 @@ static inline void __buffer_unlink_first(struct journal_head *jh)
 }
 
 /*
- * Unlink a buffer from a transaction checkpoint(io) list.
- *
- * Called with j_list_lock held.
- */
-static inline void __buffer_unlink(struct journal_head *jh)
-{
-	transaction_t *transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-	if (transaction->t_checkpoint_io_list == jh) {
-		transaction->t_checkpoint_io_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_io_list == jh)
-			transaction->t_checkpoint_io_list = NULL;
-	}
-}
-
-/*
- * Move a buffer from the checkpoint list to the checkpoint io list
- *
- * Called with j_list_lock held
- */
-static inline void __buffer_relink_io(struct journal_head *jh)
-{
-	transaction_t *transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-
-	if (!transaction->t_checkpoint_io_list) {
-		jh->b_cpnext = jh->b_cpprev = jh;
-	} else {
-		jh->b_cpnext = transaction->t_checkpoint_io_list;
-		jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
-		jh->b_cpprev->b_cpnext = jh;
-		jh->b_cpnext->b_cpprev = jh;
-	}
-	transaction->t_checkpoint_io_list = jh;
-}
-
-/*
  * Check a checkpoint buffer could be release or not.
  *
  * Requires j_list_lock
@@ -183,6 +144,7 @@ __flush_batch(journal_t *journal, int *batch_count)
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
+		journal->j_chkpt_bhs[i] = NULL;
 	}
 	*batch_count = 0;
 }
@@ -242,15 +204,6 @@ restart:
 		jh = transaction->t_checkpoint_list;
 		bh = jh2bh(jh);
 
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			goto retry;
-		}
 		if (jh->b_transaction != NULL) {
 			transaction_t *t = jh->b_transaction;
 			tid_t tid = t->t_tid;
@@ -285,30 +238,50 @@ restart:
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
-		if (!buffer_dirty(bh)) {
+		if (!trylock_buffer(bh)) {
+			/*
+			 * The buffer is locked, it may be writing back, or
+			 * flushing out in the last couple of cycles, or
+			 * re-adding into a new transaction, need to check
+			 * it again until it's unlocked.
+			 */
+			get_bh(bh);
+			spin_unlock(&journal->j_list_lock);
+			wait_on_buffer(bh);
+			/* the journal_head may have gone by now */
+			BUFFER_TRACE(bh, "brelse");
+			__brelse(bh);
+			goto retry;
+		} else if (!buffer_dirty(bh)) {
+			unlock_buffer(bh);
 			BUFFER_TRACE(bh, "remove from checkpoint");
-			if (__jbd2_journal_remove_checkpoint(jh))
-				/* The transaction was released; we're done */
+			/*
+			 * If the transaction was released or the checkpoint
+			 * list was empty, we're done.
+			 */
+			if (__jbd2_journal_remove_checkpoint(jh) ||
+			    !transaction->t_checkpoint_list)
 				goto out;
-			continue;
+		} else {
+			unlock_buffer(bh);
+			/*
+			 * We are about to write the buffer, it could be
+			 * raced by some other transaction shrink or buffer
+			 * re-log logic once we release the j_list_lock,
+			 * leave it on the checkpoint list and check status
+			 * again to make sure it's clean.
+			 */
+			BUFFER_TRACE(bh, "queue");
+			get_bh(bh);
+			J_ASSERT_BH(bh, !buffer_jwrite(bh));
+			journal->j_chkpt_bhs[batch_count++] = bh;
+			transaction->t_chp_stats.cs_written++;
+			transaction->t_checkpoint_list = jh->b_cpnext;
 		}
-		/*
-		 * Important: we are about to write the buffer, and
-		 * possibly block, while still holding the journal
-		 * lock.  We cannot afford to let the transaction
-		 * logic start messing around with this buffer before
-		 * we write it to disk, as that would break
-		 * recoverability.
-		 */
-		BUFFER_TRACE(bh, "queue");
-		get_bh(bh);
-		J_ASSERT_BH(bh, !buffer_jwrite(bh));
-		journal->j_chkpt_bhs[batch_count++] = bh;
-		__buffer_relink_io(jh);
-		transaction->t_chp_stats.cs_written++;
+
 		if ((batch_count == JBD2_NR_BATCH) ||
-		    need_resched() ||
-		    spin_needbreak(&journal->j_list_lock))
+		    need_resched() || spin_needbreak(&journal->j_list_lock) ||
+		    jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0])
 			goto unlock_and_flush;
 	}
 
@@ -322,38 +295,6 @@ restart:
 			goto restart;
 	}
 
-	/*
-	 * Now we issued all of the transaction's buffers, let's deal
-	 * with the buffers that are out for I/O.
-	 */
-restart2:
-	/* Did somebody clean up the transaction in the meanwhile? */
-	if (journal->j_checkpoint_transactions != transaction ||
-	    transaction->t_tid != this_tid)
-		goto out;
-
-	while (transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
-		bh = jh2bh(jh);
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart2;
-		}
-
-		/*
-		 * Now in whatever state the buffer currently is, we
-		 * know that it has been written out and so we can
-		 * drop it from the list
-		 */
-		if (__jbd2_journal_remove_checkpoint(jh))
-			break;
-	}
 out:
 	spin_unlock(&journal->j_list_lock);
 	result = jbd2_cleanup_journal_tail(journal);
@@ -409,49 +350,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 /* Checkpoint list management */
 
 /*
- * journal_clean_one_cp_list
- *
- * Find all the written-back checkpoint buffers in the given list and
- * release them. If 'destroy' is set, clean all buffers unconditionally.
- *
- * Called with j_list_lock held.
- * Returns 1 if we freed the transaction, 0 otherwise.
- */
-static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy)
-{
-	struct journal_head *last_jh;
-	struct journal_head *next_jh = jh;
-
-	if (!jh)
-		return 0;
-
-	last_jh = jh->b_cpprev;
-	do {
-		jh = next_jh;
-		next_jh = jh->b_cpnext;
-
-		if (!destroy && __cp_buffer_busy(jh))
-			return 0;
-
-		if (__jbd2_journal_remove_checkpoint(jh))
-			return 1;
-		/*
-		 * This function only frees up some memory
-		 * if possible so we dont have an obligation
-		 * to finish processing. Bail out if preemption
-		 * requested:
-		 */
-		if (need_resched())
-			return 0;
-	} while (jh != last_jh);
-
-	return 0;
-}
-
-/*
  * journal_shrink_one_cp_list
  *
- * Find 'nr_to_scan' written-back checkpoint buffers in the given list
+ * Find all the written-back checkpoint buffers in the given list
  * and try to release them. If the whole transaction is released, set
  * the 'released' parameter. Return the number of released checkpointed
  * buffers.
@@ -459,15 +360,15 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy)
  * Called with j_list_lock held.
  */
 static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
-						unsigned long *nr_to_scan,
-						bool *released)
+						bool destroy, bool *released)
 {
 	struct journal_head *last_jh;
 	struct journal_head *next_jh = jh;
 	unsigned long nr_freed = 0;
 	int ret;
 
-	if (!jh || *nr_to_scan == 0)
+	*released = false;
+	if (!jh)
 		return 0;
 
 	last_jh = jh->b_cpprev;
@@ -475,12 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
 
-		(*nr_to_scan)--;
-		if (__cp_buffer_busy(jh))
-			continue;
+		if (destroy) {
+			ret = __jbd2_journal_remove_checkpoint(jh);
+		} else {
+			ret = jbd2_journal_try_remove_checkpoint(jh);
+			if (ret < 0)
+				continue;
+		}
 
 		nr_freed++;
-		ret = __jbd2_journal_remove_checkpoint(jh);
 		if (ret) {
 			*released = true;
 			break;
@@ -488,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 
 		if (need_resched())
 			break;
-	} while (jh != last_jh && *nr_to_scan);
+	} while (jh != last_jh);
 
 	return nr_freed;
 }
@@ -506,11 +410,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 						  unsigned long *nr_to_scan)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	bool released;
+	bool __maybe_unused released;
 	tid_t first_tid = 0, last_tid = 0, next_tid = 0;
 	tid_t tid = 0;
 	unsigned long nr_freed = 0;
-	unsigned long nr_scanned = *nr_to_scan;
+	unsigned long freed;
 
 again:
 	spin_lock(&journal->j_list_lock);
@@ -539,19 +443,11 @@ again:
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
 		tid = transaction->t_tid;
-		released = false;
-
-		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-						       nr_to_scan, &released);
-		if (*nr_to_scan == 0)
-			break;
-		if (need_resched() || spin_needbreak(&journal->j_list_lock))
-			break;
-		if (released)
-			continue;
 
-		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list,
-						       nr_to_scan, &released);
+		freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+						   false, &released);
+		nr_freed += freed;
+		(*nr_to_scan) -= min(*nr_to_scan, freed);
 		if (*nr_to_scan == 0)
 			break;
 		if (need_resched() || spin_needbreak(&journal->j_list_lock))
@@ -572,9 +468,8 @@ again:
 	if (*nr_to_scan && next_tid)
 		goto again;
 out:
-	nr_scanned -= *nr_to_scan;
 	trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid,
-					  nr_freed, nr_scanned, next_tid);
+					  nr_freed, next_tid);
 
 	return nr_freed;
 }
@@ -590,7 +485,7 @@ out:
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	int ret;
+	bool released;
 
 	transaction = journal->j_checkpoint_transactions;
 	if (!transaction)
@@ -601,8 +496,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 	do {
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
-		ret = journal_clean_one_cp_list(transaction->t_checkpoint_list,
-						destroy);
+		journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+					   destroy, &released);
 		/*
 		 * This function only frees up some memory if possible so we
 		 * dont have an obligation to finish processing. Bail out if
@@ -610,23 +505,12 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 		 */
 		if (need_resched())
 			return;
-		if (ret)
-			continue;
-		/*
-		 * It is essential that we are as careful as in the case of
-		 * t_checkpoint_list with removing the buffer from the list as
-		 * we can possibly see not yet submitted buffers on io_list
-		 */
-		ret = journal_clean_one_cp_list(transaction->
-				t_checkpoint_io_list, destroy);
-		if (need_resched())
-			return;
 		/*
 		 * Stop scanning if we couldn't free the transaction. This
 		 * avoids pointless scanning of transactions which still
 		 * weren't checkpointed.
 		 */
-		if (!ret)
+		if (!released)
 			return;
 	} while (transaction != last_transaction);
 }
@@ -705,7 +589,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	jbd2_journal_put_journal_head(jh);
 
 	/* Is this transaction empty? */
-	if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list)
+	if (transaction->t_checkpoint_list)
 		return 0;
 
 	/*
@@ -737,6 +621,34 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 }
 
 /*
+ * Check the checkpoint buffer and try to remove it from the checkpoint
+ * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if
+ * it frees the transaction, 0 otherwise.
+ *
+ * This function is called with j_list_lock held.
+ */
+int jbd2_journal_try_remove_checkpoint(struct journal_head *jh)
+{
+	struct buffer_head *bh = jh2bh(jh);
+
+	if (!trylock_buffer(bh))
+		return -EBUSY;
+	if (buffer_dirty(bh)) {
+		unlock_buffer(bh);
+		return -EBUSY;
+	}
+	unlock_buffer(bh);
+
+	/*
+	 * Buffer is clean and the IO has finished (we held the buffer
+	 * lock) so the checkpoint is done. We can safely remove the
+	 * buffer from this transaction.
+	 */
+	JBUFFER_TRACE(jh, "remove from checkpoint list");
+	return __jbd2_journal_remove_checkpoint(jh);
+}
+
+/*
  * journal_insert_checkpoint: put a committed buffer onto a checkpoint
  * list so that we know when it is safe to clean the transaction out of
  * the log.
@@ -797,7 +709,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 	J_ASSERT(transaction->t_forget == NULL);
 	J_ASSERT(transaction->t_shadow_list == NULL);
 	J_ASSERT(transaction->t_checkpoint_list == NULL);
-	J_ASSERT(transaction->t_checkpoint_io_list == NULL);
 	J_ASSERT(atomic_read(&transaction->t_updates) == 0);
 	J_ASSERT(journal->j_committing_transaction != transaction);
 	J_ASSERT(journal->j_running_transaction != transaction);