X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Fjbd%2Fcommit.c;h=be4648bc7a2f8febe584a999040599bac87edfb6;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=002ad2bbc76992b6acda52def147799886147693;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git

diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 002ad2bbc..be4648bc7 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -1,5 +1,5 @@
 /*
- * linux/fs/commit.c
+ * linux/fs/jbd/commit.c
  *
  * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
  *
@@ -160,6 +160,121 @@ static int journal_write_commit_record(journal_t *journal,
 	return (ret == -EIO);
 }
 
+static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
+{
+	int i;
+
+	for (i = 0; i < bufs; i++) {
+		wbuf[i]->b_end_io = end_buffer_write_sync;
+		/* We use-up our safety reference in submit_bh() */
+		submit_bh(WRITE, wbuf[i]);
+	}
+}
+
+/*
+ *  Submit all the data buffers to disk
+ */
+static void journal_submit_data_buffers(journal_t *journal,
+				transaction_t *commit_transaction)
+{
+	struct journal_head *jh;
+	struct buffer_head *bh;
+	int locked;
+	int bufs = 0;
+	struct buffer_head **wbuf = journal->j_wbuf;
+
+	/*
+	 * Whenever we unlock the journal and sleep, things can get added
+	 * onto ->t_sync_datalist, so we have to keep looping back to
+	 * write_out_data until we *know* that the list is empty.
+	 *
+	 * Cleanup any flushed data buffers from the data list.  Even in
+	 * abort mode, we want to flush this out as soon as possible.
+	 */
+write_out_data:
+	cond_resched();
+	spin_lock(&journal->j_list_lock);
+
+	while (commit_transaction->t_sync_datalist) {
+		jh = commit_transaction->t_sync_datalist;
+		bh = jh2bh(jh);
+		locked = 0;
+
+		/* Get reference just to make sure buffer does not disappear
+		 * when we are forced to drop various locks */
+		get_bh(bh);
+		/* If the buffer is dirty, we need to submit IO and hence
+		 * we need the buffer lock. We try to lock the buffer without
+		 * blocking. If we fail, we need to drop j_list_lock and do
+		 * blocking lock_buffer().
+		 */
+		if (buffer_dirty(bh)) {
+			if (test_set_buffer_locked(bh)) {
+				BUFFER_TRACE(bh, "needs blocking lock");
+				spin_unlock(&journal->j_list_lock);
+				/* Write out all data to prevent deadlocks */
+				journal_do_submit_data(wbuf, bufs);
+				bufs = 0;
+				lock_buffer(bh);
+				spin_lock(&journal->j_list_lock);
+			}
+			locked = 1;
+		}
+		/* We have to get bh_state lock. Again out of order, sigh. */
+		if (!inverted_lock(journal, bh)) {
+			jbd_lock_bh_state(bh);
+			spin_lock(&journal->j_list_lock);
+		}
+		/* Someone already cleaned up the buffer? */
+		if (!buffer_jbd(bh)
+			|| jh->b_transaction != commit_transaction
+			|| jh->b_jlist != BJ_SyncData) {
+			jbd_unlock_bh_state(bh);
+			if (locked)
+				unlock_buffer(bh);
+			BUFFER_TRACE(bh, "already cleaned up");
+			put_bh(bh);
+			continue;
+		}
+		if (locked && test_clear_buffer_dirty(bh)) {
+			BUFFER_TRACE(bh, "needs writeout, adding to array");
+			wbuf[bufs++] = bh;
+			__journal_file_buffer(jh, commit_transaction,
+						BJ_Locked);
+			jbd_unlock_bh_state(bh);
+			if (bufs == journal->j_wbufsize) {
+				spin_unlock(&journal->j_list_lock);
+				journal_do_submit_data(wbuf, bufs);
+				bufs = 0;
+				goto write_out_data;
+			}
+		} else if (!locked && buffer_locked(bh)) {
+			__journal_file_buffer(jh, commit_transaction,
+						BJ_Locked);
+			jbd_unlock_bh_state(bh);
+			put_bh(bh);
+		} else {
+			BUFFER_TRACE(bh, "writeout complete: unfile");
+			__journal_unfile_buffer(jh);
+			jbd_unlock_bh_state(bh);
+			if (locked)
+				unlock_buffer(bh);
+			journal_remove_journal_head(bh);
+			/* Once for our safety reference, once for
+			 * journal_remove_journal_head() */
+			put_bh(bh);
+			put_bh(bh);
+		}
+
+		if (lock_need_resched(&journal->j_list_lock)) {
+			spin_unlock(&journal->j_list_lock);
+			goto write_out_data;
+		}
+	}
+	spin_unlock(&journal->j_list_lock);
+	journal_do_submit_data(wbuf, bufs);
+}
+
 /*
  * journal_commit_transaction
  *
@@ -261,7 +376,7 @@ void journal_commit_transaction(journal_t *journal)
 			struct buffer_head *bh = jh2bh(jh);
 
 			jbd_lock_bh_state(bh);
-			kfree(jh->b_committed_data);
+			jbd_slab_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			jbd_unlock_bh_state(bh);
 		}
@@ -313,80 +428,13 @@ void journal_commit_transaction(journal_t *journal)
 	 * Now start flushing things to disk, in the order they appear
 	 * on the transaction lists.  Data blocks go first.
 	 */
-
 	err = 0;
-	/*
-	 * Whenever we unlock the journal and sleep, things can get added
-	 * onto ->t_sync_datalist, so we have to keep looping back to
-	 * write_out_data until we *know* that the list is empty.
-	 */
-	bufs = 0;
-	/*
-	 * Cleanup any flushed data buffers from the data list.  Even in
-	 * abort mode, we want to flush this out as soon as possible.
-	 */
-write_out_data:
-	cond_resched();
-	spin_lock(&journal->j_list_lock);
-
-	while (commit_transaction->t_sync_datalist) {
-		struct buffer_head *bh;
-
-		jh = commit_transaction->t_sync_datalist;
-		commit_transaction->t_sync_datalist = jh->b_tnext;
-		bh = jh2bh(jh);
-		if (buffer_locked(bh)) {
-			BUFFER_TRACE(bh, "locked");
-			if (!inverted_lock(journal, bh))
-				goto write_out_data;
-			__journal_temp_unlink_buffer(jh);
-			__journal_file_buffer(jh, commit_transaction,
-						BJ_Locked);
-			jbd_unlock_bh_state(bh);
-			if (lock_need_resched(&journal->j_list_lock)) {
-				spin_unlock(&journal->j_list_lock);
-				goto write_out_data;
-			}
-		} else {
-			if (buffer_dirty(bh)) {
-				BUFFER_TRACE(bh, "start journal writeout");
-				get_bh(bh);
-				wbuf[bufs++] = bh;
-				if (bufs == journal->j_wbufsize) {
-					jbd_debug(2, "submit %d writes\n",
-							bufs);
-					spin_unlock(&journal->j_list_lock);
-					ll_rw_block(SWRITE, bufs, wbuf);
-					journal_brelse_array(wbuf, bufs);
-					bufs = 0;
-					goto write_out_data;
-				}
-			} else {
-				BUFFER_TRACE(bh, "writeout complete: unfile");
-				if (!inverted_lock(journal, bh))
-					goto write_out_data;
-				__journal_unfile_buffer(jh);
-				jbd_unlock_bh_state(bh);
-				journal_remove_journal_head(bh);
-				put_bh(bh);
-				if (lock_need_resched(&journal->j_list_lock)) {
-					spin_unlock(&journal->j_list_lock);
-					goto write_out_data;
-				}
-			}
-		}
-	}
-
-	if (bufs) {
-		spin_unlock(&journal->j_list_lock);
-		ll_rw_block(SWRITE, bufs, wbuf);
-		journal_brelse_array(wbuf, bufs);
-		spin_lock(&journal->j_list_lock);
-	}
+	journal_submit_data_buffers(journal, commit_transaction);
 
 	/*
 	 * Wait for all previously submitted IO to complete.
 	 */
+	spin_lock(&journal->j_list_lock);
 	while (commit_transaction->t_locked_list) {
 		struct buffer_head *bh;
 
@@ -745,14 +793,14 @@ restart_loop:
 		 * Otherwise, we can just throw away the frozen data now.
 		 */
 		if (jh->b_committed_data) {
-			kfree(jh->b_committed_data);
+			jbd_slab_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
 			}
 		} else if (jh->b_frozen_data) {
-			kfree(jh->b_frozen_data);
+			jbd_slab_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
 		}
 
@@ -790,11 +838,22 @@ restart_loop:
 			jbd_unlock_bh_state(bh);
 		} else {
 			J_ASSERT_BH(bh, !buffer_dirty(bh));
-			J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
-			__journal_unfile_buffer(jh);
-			jbd_unlock_bh_state(bh);
-			journal_remove_journal_head(bh);  /* needs a brelse */
-			release_buffer_page(bh);
+			/* The buffer on BJ_Forget list and not jbddirty means
+			 * it has been freed by this transaction and hence it
+			 * could not have been reallocated until this
+			 * transaction has committed. *BUT* it could be
+			 * reallocated once we have written all the data to
+			 * disk and before we process the buffer on BJ_Forget
+			 * list. */
+			JBUFFER_TRACE(jh, "refile or unfile freed buffer");
+			__journal_refile_buffer(jh);
+			if (!jh->b_transaction) {
+				jbd_unlock_bh_state(bh);
+				 /* needs a brelse */
+				journal_remove_journal_head(bh);
+				release_buffer_page(bh);
+			} else
+				jbd_unlock_bh_state(bh);
 		}
 		cond_resched_lock(&journal->j_list_lock);
 	}