Merge branch 'linus' into irq/genirq

2 files changed, 45 insertions, 20 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 56675306ed81..58144102bf25 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -37,10 +37,10 @@
 #include <linux/proc_fs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/math64.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
-#include <asm/div64.h>
 
 EXPORT_SYMBOL(jbd2_journal_start);
 EXPORT_SYMBOL(jbd2_journal_restart);
@@ -450,7 +450,7 @@ int __jbd2_log_space_left(journal_t *journal)
 }
 
 /*
- * Called under j_state_lock.  Returns true if a transaction was started.
+ * Called under j_state_lock.  Returns true if a transaction commit was started.
  */
 int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 {
@@ -518,7 +518,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 
 /*
  * Start a commit of the current running transaction (if any).  Returns true
- * if a transaction was started, and fills its tid in at *ptid
+ * if a transaction is going to be committed (or is currently already
+ * committing), and fills its tid in at *ptid
  */
 int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 {
@@ -528,15 +529,19 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
         if (journal->j_running_transaction) {
                 tid_t tid = journal->j_running_transaction->t_tid;
 
-                ret = __jbd2_log_start_commit(journal, tid);
-                if (ret && ptid)
+                __jbd2_log_start_commit(journal, tid);
+                /* There's a running transaction and we've just made sure
+                 * it's commit has been scheduled. */
+                if (ptid)
                         *ptid = tid;
-        } else if (journal->j_committing_transaction && ptid) {
+                ret = 1;
+        } else if (journal->j_committing_transaction) {
                 /*
                  * If ext3_write_super() recently started a commit, then we
                  * have to wait for completion of that transaction
                  */
-                *ptid = journal->j_committing_transaction->t_tid;
+                if (ptid)
+                        *ptid = journal->j_committing_transaction->t_tid;
                 ret = 1;
         }
         spin_unlock(&journal->j_state_lock);
@@ -846,8 +851,8 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v)
             jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
         seq_printf(seq, "  %ums logging transaction\n",
             jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
-        seq_printf(seq, "  %luus average transaction commit time\n",
-                   do_div(s->journal->j_average_commit_time, 1000));
+        seq_printf(seq, "  %lluus average transaction commit time\n",
+                   div_u64(s->journal->j_average_commit_time, 1000));
         seq_printf(seq, "  %lu handles per transaction\n",
             s->stats->u.run.rs_handle_count / s->stats->ts_tid);
         seq_printf(seq, "  %lu blocks per transaction\n",
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7d..28ce21d8598e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2129,26 +2129,46 @@ done:
 }
 
 /*
- * This function must be called when inode is journaled in ordered mode
- * before truncation happens. It starts writeout of truncated part in
- * case it is in the committing transaction so that we stand to ordered
- * mode consistency guarantees.
+ * File truncate and transaction commit interact with each other in a
+ * non-trivial way.  If a transaction writing data block A is
+ * committing, we cannot discard the data by truncate until we have
+ * written them.  Otherwise if we crashed after the transaction with
+ * write has committed but before the transaction with truncate has
+ * committed, we could see stale data in block A.  This function is a
+ * helper to solve this problem.  It starts writeout of the truncated
+ * part in case it is in the committing transaction.
+ *
+ * Filesystem code must call this function when inode is journaled in
+ * ordered mode before truncation happens and after the inode has been
+ * placed on orphan list with the new inode size. The second condition
+ * avoids the race that someone writes new data and we start
+ * committing the transaction after this function has been called but
+ * before a transaction for truncate is started (and furthermore it
+ * allows us to optimize the case where the addition to orphan list
+ * happens in the same transaction as write --- we don't have to write
+ * any data in such case).
  */
-int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+int jbd2_journal_begin_ordered_truncate(journal_t *journal,
+                                        struct jbd2_inode *jinode,
                                         loff_t new_size)
 {
-        journal_t *journal;
-        transaction_t *commit_trans;
+        transaction_t *inode_trans, *commit_trans;
         int ret = 0;
 
-        if (!inode->i_transaction && !inode->i_next_transaction)
+        /* This is a quick check to avoid locking if not necessary */
+        if (!jinode->i_transaction)
                 goto out;
-        journal = inode->i_transaction->t_journal;
+        /* Locks are here just to force reading of recent values, it is
+         * enough that the transaction was not committing before we started
+         * a transaction adding the inode to orphan list */
         spin_lock(&journal->j_state_lock);
         commit_trans = journal->j_committing_transaction;
         spin_unlock(&journal->j_state_lock);
-        if (inode->i_transaction == commit_trans) {
-                ret = filemap_fdatawrite_range(inode->i_vfs_inode->i_mapping,
+        spin_lock(&journal->j_list_lock);
+        inode_trans = jinode->i_transaction;
+        spin_unlock(&journal->j_list_lock);
+        if (inode_trans == commit_trans) {
+                ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping,
                         new_size, LLONG_MAX);
                 if (ret)
                         jbd2_journal_abort(journal, ret);