Merge commit 'v2.6.30-rc1' into sched/urgent

Merge reason: update to latest upstream to queue up fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 75 insertions, 26 deletions

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 62804e57a44c..073c8c3df7cd 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -138,7 +138,7 @@ static int journal_submit_commit_record(journal_t *journal,
                 set_buffer_ordered(bh);
                 barrier_done = 1;
         }
-        ret = submit_bh(WRITE_SYNC, bh);
+        ret = submit_bh(WRITE_SYNC_PLUG, bh);
         if (barrier_done)
                 clear_buffer_ordered(bh);
 
@@ -159,7 +159,7 @@ static int journal_submit_commit_record(journal_t *journal,
                 lock_buffer(bh);
                 set_buffer_uptodate(bh);
                 clear_buffer_dirty(bh);
-                ret = submit_bh(WRITE_SYNC, bh);
+                ret = submit_bh(WRITE_SYNC_PLUG, bh);
         }
         *cbh = bh;
         return ret;
@@ -190,7 +190,7 @@ retry:
                 set_buffer_uptodate(bh);
                 bh->b_end_io = journal_end_buffer_io_sync;
 
-                ret = submit_bh(WRITE_SYNC, bh);
+                ret = submit_bh(WRITE_SYNC_PLUG, bh);
                 if (ret) {
                         unlock_buffer(bh);
                         return ret;
@@ -367,6 +367,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         int tag_bytes = journal_tag_bytes(journal);
         struct buffer_head *cbh = NULL; /* For transactional checksums */
         __u32 crc32_sum = ~0;
+        int write_op = WRITE;
 
         /*
          * First job: lock down the current transaction and wait for
@@ -401,6 +402,13 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         spin_lock(&journal->j_state_lock);
         commit_transaction->t_state = T_LOCKED;
 
+        /*
+         * Use plugged writes here, since we want to submit several before
+         * we unplug the device. We don't do explicit unplugging in here,
+         * instead we rely on sync_buffer() doing the unplug for us.
+         */
+        if (commit_transaction->t_synchronous_commit)
+                write_op = WRITE_SYNC_PLUG;
         stats.u.run.rs_wait = commit_transaction->t_max_wait;
         stats.u.run.rs_locked = jiffies;
         stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
@@ -680,7 +688,7 @@ start_journal_io:
                                 clear_buffer_dirty(bh);
                                 set_buffer_uptodate(bh);
                                 bh->b_end_io = journal_end_buffer_io_sync;
-                                submit_bh(WRITE, bh);
+                                submit_bh(write_op, bh);
                         }
                         cond_resched();
                         stats.u.run.rs_blocks_logged += bufs;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index eb343008eded..58144102bf25 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -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);
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 257ff2625765..bbe6d592d8b3 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -55,6 +55,25 @@
  *                      need do nothing.
  * RevokeValid set, Revoked set:
  *                      buffer has been revoked.
+ *
+ * Locking rules:
+ * We keep two hash tables of revoke records. One hashtable belongs to the
+ * running transaction (is pointed to by journal->j_revoke), the other one
+ * belongs to the committing transaction. Accesses to the second hash table
+ * happen only from the kjournald and no other thread touches this table.  Also
+ * journal_switch_revoke_table() which switches which hashtable belongs to the
+ * running and which to the committing transaction is called only from
+ * kjournald. Therefore we need no locks when accessing the hashtable belonging
+ * to the committing transaction.
+ *
+ * All users operating on the hash table belonging to the running transaction
+ * have a handle to the transaction. Therefore they are safe from kjournald
+ * switching hash tables under them. For operations on the lists of entries in
+ * the hash table j_revoke_lock is used.
+ *
+ * Finally, also replay code uses the hash tables but at this moment noone else
+ * can touch them (filesystem isn't mounted yet) and hence no locking is
+ * needed.
  */
 
 #ifndef __KERNEL__
@@ -401,8 +420,6 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
  * the second time we would still have a pending revoke to cancel.  So,
  * do not trust the Revoked bit on buffers unless RevokeValid is also
  * set.
- *
- * The caller must have the journal locked.
  */
 int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 {
@@ -480,10 +497,7 @@ void jbd2_journal_switch_revoke_table(journal_t *journal)
 /*
  * Write revoke records to the journal for all entries in the current
  * revoke hash, deleting the entries as we go.
- *
- * Called with the journal lock held.
  */
-
 void jbd2_journal_write_revoke_records(journal_t *journal,
                                   transaction_t *transaction)
 {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 46b4e347ed7d..996ffda06bf3 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1315,6 +1315,8 @@ int jbd2_journal_stop(handle_t *handle)
                 }
         }
 
+        if (handle->h_sync)
+                transaction->t_synchronous_commit = 1;
         current->journal_info = NULL;
         spin_lock(&journal->j_state_lock);
         spin_lock(&transaction->t_handle_lock);
@@ -2129,26 +2131,46 @@ 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);