#include <linux/fs.h>
#include <linux/jbd.h>
#include <linux/errno.h>
-#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
+#include <linux/bio.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
return (ret == -EIO);
}
-static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
+static void journal_do_submit_data(struct buffer_head **wbuf, int bufs,
+ int write_op)
{
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_bh(write_op, wbuf[i]);
}
}
* Submit all the data buffers to disk
*/
static int journal_submit_data_buffers(journal_t *journal,
- transaction_t *commit_transaction)
+ transaction_t *commit_transaction,
+ int write_op)
{
struct journal_head *jh;
struct buffer_head *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);
+ journal_do_submit_data(wbuf, bufs, write_op);
bufs = 0;
lock_buffer(bh);
spin_lock(&journal->j_list_lock);
spin_lock(&journal->j_list_lock);
}
/* Someone already cleaned up the buffer? */
- if (!buffer_jbd(bh)
+ if (!buffer_jbd(bh) || bh2jh(bh) != jh
|| jh->b_transaction != commit_transaction
|| jh->b_jlist != BJ_SyncData) {
jbd_unlock_bh_state(bh);
jbd_unlock_bh_state(bh);
if (bufs == journal->j_wbufsize) {
spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
+ journal_do_submit_data(wbuf, bufs, write_op);
bufs = 0;
goto write_out_data;
}
}
}
spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
+ journal_do_submit_data(wbuf, bufs, write_op);
return err;
}
int bufs;
int flags;
int err;
- unsigned long blocknr;
+ unsigned int blocknr;
ktime_t start_time;
u64 commit_time;
char *tagp = NULL;
int first_tag = 0;
int tag_flag;
int i;
+ int write_op = WRITE;
/*
* First job: lock down the current transaction and wait for
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;
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
DEFINE_WAIT(wait);
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
- err = journal_submit_data_buffers(journal, commit_transaction);
+ err = journal_submit_data_buffers(journal, commit_transaction,
+ write_op);
/*
* Wait for all previously submitted IO to complete.
spin_lock(&journal->j_list_lock);
continue;
}
- if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
+ if (buffer_jbd(bh) && bh2jh(bh) == jh &&
+ jh->b_transaction == commit_transaction &&
+ jh->b_jlist == BJ_Locked) {
__journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
journal_remove_journal_head(bh);
err = 0;
}
- journal_write_revoke_records(journal, commit_transaction);
+ journal_write_revoke_records(journal, commit_transaction, write_op);
/*
* If we found any dirty or locked buffers, then we should have
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();
jbd_debug(3, "JBD: commit phase 6\n");
+ /* All metadata is written, now write commit record and do cleanup */
+ spin_lock(&journal->j_state_lock);
+ J_ASSERT(commit_transaction->t_state == T_COMMIT);
+ commit_transaction->t_state = T_COMMIT_RECORD;
+ spin_unlock(&journal->j_state_lock);
+
if (journal_write_commit_record(journal, commit_transaction))
err = -EIO;
/* A buffer which has been freed while still being
* journaled by a previous transaction may end up still
* being dirty here, but we want to avoid writing back
- * that buffer in the future now that the last use has
- * been committed. That's not only a performance gain,
- * it also stops aliasing problems if the buffer is left
- * behind for writeback and gets reallocated for another
+ * that buffer in the future after the "add to orphan"
+ * operation been committed, That's not only a performance
+ * gain, it also stops aliasing problems if the buffer is
+ * left behind for writeback and gets reallocated for another
* use in a different page. */
- if (buffer_freed(bh)) {
+ if (buffer_freed(bh) && !jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
}
jbd_debug(3, "JBD: commit phase 8\n");
- J_ASSERT(commit_transaction->t_state == T_COMMIT);
+ J_ASSERT(commit_transaction->t_state == T_COMMIT_RECORD);
commit_transaction->t_state = T_FINISHED;
J_ASSERT(commit_transaction == journal->j_committing_transaction);