4 files changed, 145 insertions, 68 deletions

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 91389c8aee8a..9203c3332f17 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -20,6 +20,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 
@@ -93,7 +94,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
         int ret = 0;
         struct buffer_head *bh = jh2bh(jh);
 
-        if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+        if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+            !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
                 JBUFFER_TRACE(jh, "remove from checkpoint list");
                 ret = __jbd2_journal_remove_checkpoint(jh) + 1;
                 jbd_unlock_bh_state(bh);
@@ -126,14 +128,29 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 
                 /*
                  * Test again, another process may have checkpointed while we
-                 * were waiting for the checkpoint lock
+                 * were waiting for the checkpoint lock. If there are no
+                 * outstanding transactions there is nothing to checkpoint and
+                 * we can't make progress. Abort the journal in this case.
                  */
                 spin_lock(&journal->j_state_lock);
+                spin_lock(&journal->j_list_lock);
                 nblocks = jbd_space_needed(journal);
                 if (__jbd2_log_space_left(journal) < nblocks) {
+                        int chkpt = journal->j_checkpoint_transactions != NULL;
+
+                        spin_unlock(&journal->j_list_lock);
                         spin_unlock(&journal->j_state_lock);
-                        jbd2_log_do_checkpoint(journal);
+                        if (chkpt) {
+                                jbd2_log_do_checkpoint(journal);
+                        } else {
+                                printk(KERN_ERR "%s: no transactions\n",
+                                       __func__);
+                                jbd2_journal_abort(journal, 0);
+                        }
+
                         spin_lock(&journal->j_state_lock);
+                } else {
+                        spin_unlock(&journal->j_list_lock);
                 }
                 mutex_unlock(&journal->j_checkpoint_mutex);
         }
@@ -160,21 +177,25 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
  * buffers. Note that we take the buffers in the opposite ordering
  * from the one in which they were submitted for IO.
  *
+ * Return 0 on success, and return <0 if some buffers have failed
+ * to be written out.
+ *
  * Called with j_list_lock held.
  */
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
 {
         struct journal_head *jh;
         struct buffer_head *bh;
         tid_t this_tid;
         int released = 0;
+        int ret = 0;
 
         this_tid = transaction->t_tid;
 restart:
         /* Did somebody clean up the transaction in the meanwhile? */
         if (journal->j_checkpoint_transactions != transaction ||
                         transaction->t_tid != this_tid)
-                return;
+                return ret;
         while (!released && transaction->t_checkpoint_io_list) {
                 jh = transaction->t_checkpoint_io_list;
                 bh = jh2bh(jh);
@@ -194,6 +215,9 @@ restart:
                         spin_lock(&journal->j_list_lock);
                         goto restart;
                 }
+                if (unlikely(buffer_write_io_error(bh)))
+                        ret = -EIO;
+
                 /*
                  * 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
@@ -203,6 +227,8 @@ restart:
                 jbd2_journal_remove_journal_head(bh);
                 __brelse(bh);
         }
+
+        return ret;
 }
 
 #define NR_BATCH        64
@@ -226,7 +252,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Try to flush one buffer from the checkpoint list to disk.
  *
  * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list.
+ * scan of the checkpoint list.  Return <0 if the buffer has failed to
+ * be written out.
  *
  * Called with j_list_lock held and drops it if 1 is returned
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
@@ -258,6 +285,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
                 jbd2_log_wait_commit(journal, tid);
                 ret = 1;
         } else if (!buffer_dirty(bh)) {
+                ret = 1;
+                if (unlikely(buffer_write_io_error(bh)))
+                        ret = -EIO;
                 J_ASSERT_JH(jh, !buffer_jbddirty(bh));
                 BUFFER_TRACE(bh, "remove from checkpoint");
                 __jbd2_journal_remove_checkpoint(jh);
@@ -265,7 +295,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
                 jbd_unlock_bh_state(bh);
                 jbd2_journal_remove_journal_head(bh);
                 __brelse(bh);
-                ret = 1;
         } else {
                 /*
                  * Important: we are about to write the buffer, and
@@ -298,6 +327,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
  * to disk. We submit larger chunks of data at once.
  *
  * The journal should be locked before calling this function.
+ * Called with j_checkpoint_mutex held.
  */
 int jbd2_log_do_checkpoint(journal_t *journal)
 {
@@ -313,6 +343,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
          * journal straight away.
          */
         result = jbd2_cleanup_journal_tail(journal);
+        trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d",
+                   journal->j_devname, result);
         jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
         if (result <= 0)
                 return result;
@@ -321,6 +353,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
          * OK, we need to start writing disk blocks.  Take one transaction
          * and write it.
          */
+        result = 0;
         spin_lock(&journal->j_list_lock);
         if (!journal->j_checkpoint_transactions)
                 goto out;
@@ -339,7 +372,7 @@ restart:
                 int batch_count = 0;
                 struct buffer_head *bhs[NR_BATCH];
                 struct journal_head *jh;
-                int retry = 0;
+                int retry = 0, err;
 
                 while (!retry && transaction->t_checkpoint_list) {
                         struct buffer_head *bh;
@@ -353,6 +386,8 @@ restart:
                         }
                         retry = __process_buffer(journal, jh, bhs, &batch_count,
                                                  transaction);
+                        if (retry < 0 && !result)
+                                result = retry;
                         if (!retry && (need_resched() ||
                                 spin_needbreak(&journal->j_list_lock))) {
                                 spin_unlock(&journal->j_list_lock);
@@ -377,14 +412,18 @@ restart:
                  * Now we have cleaned up the first transaction's checkpoint
                  * list. Let's clean up the second one
                  */
-                __wait_cp_io(journal, transaction);
+                err = __wait_cp_io(journal, transaction);
+                if (!result)
+                        result = err;
         }
 out:
         spin_unlock(&journal->j_list_lock);
-        result = jbd2_cleanup_journal_tail(journal);
         if (result < 0)
-                return result;
-        return 0;
+                jbd2_journal_abort(journal, result);
+        else
+                result = jbd2_cleanup_journal_tail(journal);
+
+        return (result < 0) ? result : 0;
 }
 
 /*
@@ -400,8 +439,9 @@ out:
  * This is the only part of the journaling code which really needs to be
  * aware of transaction aborts.  Checkpointing involves writing to the
  * main filesystem area rather than to the journal, so it can proceed
- * even in abort state, but we must not update the journal superblock if
- * we have an abort error outstanding.
+ * even in abort state, but we must not update the super block if
+ * checkpointing may have failed.  Otherwise, we would lose some metadata
+ * buffers which should be written-back to the filesystem.
  */
 
 int jbd2_cleanup_journal_tail(journal_t *journal)
@@ -410,6 +450,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
         tid_t           first_tid;
         unsigned long   blocknr, freed;
 
+        if (is_journal_aborted(journal))
+                return 1;
+
         /* OK, work out the oldest transaction remaining in the log, and
          * the log block it starts at.
          *
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f2ad061e95ec..0abe02c4242a 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -16,6 +16,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -126,8 +127,7 @@ static int journal_submit_commit_record(journal_t *journal,
 
         JBUFFER_TRACE(descriptor, "submit commit block");
         lock_buffer(bh);
-        get_bh(bh);
-        set_buffer_dirty(bh);
+        clear_buffer_dirty(bh);
         set_buffer_uptodate(bh);
         bh->b_end_io = journal_end_buffer_io_sync;
 
@@ -147,12 +147,9 @@ static int journal_submit_commit_record(journal_t *journal,
          * to remember if we sent a barrier request
          */
         if (ret == -EOPNOTSUPP && barrier_done) {
-                char b[BDEVNAME_SIZE];
-
                 printk(KERN_WARNING
-                        "JBD: barrier-based sync failed on %s - "
-                        "disabling barriers\n",
-                        bdevname(journal->j_dev, b));
+                       "JBD: barrier-based sync failed on %s - "
+                       "disabling barriers\n", journal->j_devname);
                 spin_lock(&journal->j_state_lock);
                 journal->j_flags &= ~JBD2_BARRIER;
                 spin_unlock(&journal->j_state_lock);
@@ -160,7 +157,7 @@ static int journal_submit_commit_record(journal_t *journal,
                 /* And try again, without the barrier */
                 lock_buffer(bh);
                 set_buffer_uptodate(bh);
-                set_buffer_dirty(bh);
+                clear_buffer_dirty(bh);
                 ret = submit_bh(WRITE, bh);
         }
         *cbh = bh;
@@ -371,6 +368,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         commit_transaction = journal->j_running_transaction;
         J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
+        trace_mark(jbd2_start_commit, "dev %s transaction %d",
+                   journal->j_devname, commit_transaction->t_tid);
         jbd_debug(1, "JBD: starting commit of transaction %d\n",
                         commit_transaction->t_tid);
 
@@ -505,9 +504,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
                 jh = commit_transaction->t_buffers;
 
                 /* If we're in abort mode, we just un-journal the buffer and
-                   release it for background writing. */
+                   release it. */
 
                 if (is_journal_aborted(journal)) {
+                        clear_buffer_jbddirty(jh2bh(jh));
                         JBUFFER_TRACE(jh, "journal is aborting: refile");
                         jbd2_journal_refile_buffer(journal, jh);
                         /* If that was the last one, we need to clean up
@@ -681,11 +681,11 @@ start_journal_io:
          */
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
         if (err) {
-                char b[BDEVNAME_SIZE];
-
                 printk(KERN_WARNING
                         "JBD2: Detected IO errors while flushing file data "
-                        "on %s\n", bdevname(journal->j_fs_dev, b));
+                       "on %s\n", journal->j_devname);
+                if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR)
+                        jbd2_journal_abort(journal, err);
                 err = 0;
         }
 
@@ -786,6 +786,9 @@ wait_for_iobuf:
                 /* AKPM: bforget here */
         }
 
+        if (err)
+                jbd2_journal_abort(journal, err);
+
         jbd_debug(3, "JBD: commit phase 5\n");
 
         if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -884,6 +887,8 @@ restart_loop:
                 if (buffer_jbddirty(bh)) {
                         JBUFFER_TRACE(jh, "add to new checkpointing trans");
                         __jbd2_journal_insert_checkpoint(jh, commit_transaction);
+                        if (is_journal_aborted(journal))
+                                clear_buffer_jbddirty(bh);
                         JBUFFER_TRACE(jh, "refile for checkpoint writeback");
                         __jbd2_journal_refile_buffer(jh);
                         jbd_unlock_bh_state(bh);
@@ -990,6 +995,9 @@ restart_loop:
         }
         spin_unlock(&journal->j_list_lock);
 
+        trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
+                   journal->j_devname, commit_transaction->t_tid,
+                   journal->j_tail_sequence);
         jbd_debug(1, "JBD: commit %d complete, head %d\n",
                   journal->j_commit_sequence, journal->j_tail_sequence);
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8207a01c4edb..783de118de92 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -597,13 +597,9 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
                 if (ret)
                         *retp = ret;
                 else {
-                        char b[BDEVNAME_SIZE];
-
                         printk(KERN_ALERT "%s: journal block not found "
                                         "at offset %lu on %s\n",
-                                __func__,
-                                blocknr,
-                                bdevname(journal->j_dev, b));
+                               __func__, blocknr, journal->j_devname);
                         err = -EIO;
                         __journal_abort_soft(journal, err);
                 }
@@ -901,10 +897,7 @@ static struct proc_dir_entry *proc_jbd2_stats;
 
 static void jbd2_stats_proc_init(journal_t *journal)
 {
-        char name[BDEVNAME_SIZE];
-
-        bdevname(journal->j_dev, name);
-        journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats);
+        journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
         if (journal->j_proc_entry) {
                 proc_create_data("history", S_IRUGO, journal->j_proc_entry,
                                  &jbd2_seq_history_fops, journal);
@@ -915,12 +908,9 @@ static void jbd2_stats_proc_init(journal_t *journal)
 
 static void jbd2_stats_proc_exit(journal_t *journal)
 {
-        char name[BDEVNAME_SIZE];
-
-        bdevname(journal->j_dev, name);
         remove_proc_entry("info", journal->j_proc_entry);
         remove_proc_entry("history", journal->j_proc_entry);
-        remove_proc_entry(name, proc_jbd2_stats);
+        remove_proc_entry(journal->j_devname, proc_jbd2_stats);
 }
 
 static void journal_init_stats(journal_t *journal)
@@ -1018,6 +1008,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 {
         journal_t *journal = journal_init_common();
         struct buffer_head *bh;
+        char *p;
         int n;
 
         if (!journal)
@@ -1039,6 +1030,10 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
         journal->j_fs_dev = fs_dev;
         journal->j_blk_offset = start;
         journal->j_maxlen = len;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
         jbd2_stats_proc_init(journal);
 
         bh = __getblk(journal->j_dev, start, journal->j_blocksize);
@@ -1061,6 +1056,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 {
         struct buffer_head *bh;
         journal_t *journal = journal_init_common();
+        char *p;
         int err;
         int n;
         unsigned long long blocknr;
@@ -1070,6 +1066,12 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 
         journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
         journal->j_inode = inode;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
+        p = journal->j_devname + strlen(journal->j_devname);
+        sprintf(p, ":%lu", journal->j_inode->i_ino);
         jbd_debug(1,
                   "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
                   journal, inode->i_sb->s_id, inode->i_ino,
@@ -1253,6 +1255,22 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
                 goto out;
         }
 
+        if (buffer_write_io_error(bh)) {
+                /*
+                 * Oh, dear.  A previous attempt to write the journal
+                 * superblock failed.  This could happen because the
+                 * USB device was yanked out.  Or it could happen to
+                 * be a transient write error and maybe the block will
+                 * be remapped.  Nothing we can do but to retry the
+                 * write and hope for the best.
+                 */
+                printk(KERN_ERR "JBD2: previous I/O error detected "
+                       "for journal superblock update for %s.\n",
+                       journal->j_devname);
+                clear_buffer_write_io_error(bh);
+                set_buffer_uptodate(bh);
+        }
+
         spin_lock(&journal->j_state_lock);
         jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
                   journal->j_tail, journal->j_tail_sequence, journal->j_errno);
@@ -1264,9 +1282,16 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 
         BUFFER_TRACE(bh, "marking dirty");
         mark_buffer_dirty(bh);
-        if (wait)
+        if (wait) {
                 sync_dirty_buffer(bh);
-        else
+                if (buffer_write_io_error(bh)) {
+                        printk(KERN_ERR "JBD2: I/O error detected "
+                               "when updating journal superblock for %s.\n",
+                               journal->j_devname);
+                        clear_buffer_write_io_error(bh);
+                        set_buffer_uptodate(bh);
+                }
+        } else
                 ll_rw_block(SWRITE, 1, &bh);
 
 out:
@@ -1426,9 +1451,12 @@ recovery_error:
  *
  * Release a journal_t structure once it is no longer in use by the
  * journaled object.
+ * Return <0 if we couldn't clean up the journal.
  */
-void jbd2_journal_destroy(journal_t *journal)
+int jbd2_journal_destroy(journal_t *journal)
 {
+        int err = 0;
+
         /* Wait for the commit thread to wake up and die. */
         journal_kill_thread(journal);
 
@@ -1451,11 +1479,16 @@ void jbd2_journal_destroy(journal_t *journal)
         J_ASSERT(journal->j_checkpoint_transactions == NULL);
         spin_unlock(&journal->j_list_lock);
 
-        /* We can now mark the journal as empty. */
-        journal->j_tail = 0;
-        journal->j_tail_sequence = ++journal->j_transaction_sequence;
         if (journal->j_sb_buffer) {
-                jbd2_journal_update_superblock(journal, 1);
+                if (!is_journal_aborted(journal)) {
+                        /* We can now mark the journal as empty. */
+                        journal->j_tail = 0;
+                        journal->j_tail_sequence =
+                                ++journal->j_transaction_sequence;
+                        jbd2_journal_update_superblock(journal, 1);
+                } else {
+                        err = -EIO;
+                }
                 brelse(journal->j_sb_buffer);
         }
 
@@ -1467,6 +1500,8 @@ void jbd2_journal_destroy(journal_t *journal)
                 jbd2_journal_destroy_revoke(journal);
         kfree(journal->j_wbuf);
         kfree(journal);
+
+        return err;
 }
 
 
@@ -1692,10 +1727,16 @@ int jbd2_journal_flush(journal_t *journal)
         spin_lock(&journal->j_list_lock);
         while (!err && journal->j_checkpoint_transactions != NULL) {
                 spin_unlock(&journal->j_list_lock);
+                mutex_lock(&journal->j_checkpoint_mutex);
                 err = jbd2_log_do_checkpoint(journal);
+                mutex_unlock(&journal->j_checkpoint_mutex);
                 spin_lock(&journal->j_list_lock);
         }
         spin_unlock(&journal->j_list_lock);
+
+        if (is_journal_aborted(journal))
+                return -EIO;
+
         jbd2_cleanup_journal_tail(journal);
 
         /* Finally, mark the journal as really needing no recovery.
@@ -1717,7 +1758,7 @@ int jbd2_journal_flush(journal_t *journal)
         J_ASSERT(journal->j_head == journal->j_tail);
         J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
         spin_unlock(&journal->j_state_lock);
-        return err;
+        return 0;
 }
 
 /**
@@ -1761,23 +1802,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 }
 
 /*
- * journal_dev_name: format a character string to describe on what
- * device this journal is present.
- */
-
-static const char *journal_dev_name(journal_t *journal, char *buffer)
-{
-        struct block_device *bdev;
-
-        if (journal->j_inode)
-                bdev = journal->j_inode->i_sb->s_bdev;
-        else
-                bdev = journal->j_dev;
-
-        return bdevname(bdev, buffer);
-}
-
-/*
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
  *
@@ -1793,13 +1817,12 @@ static const char *journal_dev_name(journal_t *journal, char *buffer)
 void __jbd2_journal_abort_hard(journal_t *journal)
 {
         transaction_t *transaction;
-        char b[BDEVNAME_SIZE];
 
         if (journal->j_flags & JBD2_ABORT)
                 return;
 
         printk(KERN_ERR "Aborting journal on device %s.\n",
-                journal_dev_name(journal, b));
+               journal->j_devname);
 
         spin_lock(&journal->j_state_lock);
         journal->j_flags |= JBD2_ABORT;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 058f50f65b76..73063285b13f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -225,7 +225,7 @@ do {									\
  */
 int jbd2_journal_recover(journal_t *journal)
 {
-        int                     err;
+        int                     err, err2;
         journal_superblock_t *  sb;
 
         struct recovery_info    info;
@@ -263,7 +263,10 @@ int jbd2_journal_recover(journal_t *journal)
         journal->j_transaction_sequence = ++info.end_transaction;
 
         jbd2_journal_clear_revoke(journal);
-        sync_blockdev(journal->j_fs_dev);
+        err2 = sync_blockdev(journal->j_fs_dev);
+        if (!err)
+                err = err2;
+
         return err;
 }