aboutsummaryrefslogtreecommitdiff
path: root/fs/jbd2/commit.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd2/commit.c')
-rw-r--r--fs/jbd2/commit.c222
1 files changed, 96 insertions, 126 deletions
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7b4088b2364d..f3ad1598b201 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -25,7 +25,10 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/bitops.h>
#include <trace/events/jbd2.h>
+#include <asm/system.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
@@ -100,7 +103,6 @@ static int journal_submit_commit_record(journal_t *journal,
struct commit_header *tmp;
struct buffer_head *bh;
int ret;
- int barrier_done = 0;
struct timespec now = current_kernel_time();
if (is_journal_aborted(journal))
@@ -133,34 +135,12 @@ static int journal_submit_commit_record(journal_t *journal,
bh->b_end_io = journal_end_buffer_io_sync;
if (journal->j_flags & JBD2_BARRIER &&
- !JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
- set_buffer_ordered(bh);
- barrier_done = 1;
- }
- ret = submit_bh(WRITE_SYNC_PLUG, bh);
- if (barrier_done)
- clear_buffer_ordered(bh);
-
- /* is it possible for another commit to fail at roughly
- * the same time as this one? If so, we don't want to
- * trust the barrier flag in the super, but instead want
- * to remember if we sent a barrier request
- */
- if (ret == -EOPNOTSUPP && barrier_done) {
- printk(KERN_WARNING
- "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);
-
- /* And try again, without the barrier */
- lock_buffer(bh);
- set_buffer_uptodate(bh);
- clear_buffer_dirty(bh);
+ !JBD2_HAS_INCOMPAT_FEATURE(journal,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
+ ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh);
+ else
ret = submit_bh(WRITE_SYNC_PLUG, bh);
- }
+
*cbh = bh;
return ret;
}
@@ -174,29 +154,8 @@ static int journal_wait_on_commit_record(journal_t *journal,
{
int ret = 0;
-retry:
clear_buffer_dirty(bh);
wait_on_buffer(bh);
- if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
- printk(KERN_WARNING
- "JBD2: wait_on_commit_record: 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);
-
- lock_buffer(bh);
- clear_buffer_dirty(bh);
- set_buffer_uptodate(bh);
- bh->b_end_io = journal_end_buffer_io_sync;
-
- ret = submit_bh(WRITE_SYNC_PLUG, bh);
- if (ret) {
- unlock_buffer(bh);
- return ret;
- }
- goto retry;
- }
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
@@ -220,7 +179,6 @@ static int journal_submit_inode_data_buffers(struct address_space *mapping)
.nr_to_write = mapping->nrpages * 2,
.range_start = 0,
.range_end = i_size_read(mapping->host),
- .for_writepages = 1,
};
ret = generic_writepages(mapping, &wbc);
@@ -245,7 +203,7 @@ static int journal_submit_data_buffers(journal_t *journal,
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
mapping = jinode->i_vfs_inode->i_mapping;
- jinode->i_flags |= JI_COMMIT_RUNNING;
+ set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
spin_unlock(&journal->j_list_lock);
/*
* submit the inode data buffers. We use writepage
@@ -259,7 +217,9 @@ static int journal_submit_data_buffers(journal_t *journal,
ret = err;
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
- jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ commit_transaction->t_flushed_data_blocks = 1;
+ clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+ smp_mb__after_clear_bit();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
spin_unlock(&journal->j_list_lock);
@@ -280,13 +240,13 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
/* For locking, see the comment in journal_submit_data_buffers() */
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
- jinode->i_flags |= JI_COMMIT_RUNNING;
+ set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
spin_unlock(&journal->j_list_lock);
err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
if (err) {
/*
* Because AS_EIO is cleared by
- * wait_on_page_writeback_range(), set it again so
+ * filemap_fdatawait_range(), set it again so
* that user process can get -EIO from fsync().
*/
set_bit(AS_EIO,
@@ -296,7 +256,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
ret = err;
}
spin_lock(&journal->j_list_lock);
- jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+ smp_mb__after_clear_bit();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
@@ -368,7 +329,7 @@ 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;
+ int write_op = WRITE_SYNC;
/*
* First job: lock down the current transaction and wait for
@@ -399,7 +360,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
jbd_debug(1, "JBD: starting commit of transaction %d\n",
commit_transaction->t_tid);
- spin_lock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
commit_transaction->t_state = T_LOCKED;
/*
@@ -410,29 +371,29 @@ void jbd2_journal_commit_transaction(journal_t *journal)
if (commit_transaction->t_synchronous_commit)
write_op = WRITE_SYNC_PLUG;
trace_jbd2_commit_locking(journal, commit_transaction);
- 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,
- stats.u.run.rs_locked);
+ stats.run.rs_wait = commit_transaction->t_max_wait;
+ stats.run.rs_locked = jiffies;
+ stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
+ stats.run.rs_locked);
spin_lock(&commit_transaction->t_handle_lock);
- while (commit_transaction->t_updates) {
+ while (atomic_read(&commit_transaction->t_updates)) {
DEFINE_WAIT(wait);
prepare_to_wait(&journal->j_wait_updates, &wait,
TASK_UNINTERRUPTIBLE);
- if (commit_transaction->t_updates) {
+ if (atomic_read(&commit_transaction->t_updates)) {
spin_unlock(&commit_transaction->t_handle_lock);
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
schedule();
- spin_lock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
spin_lock(&commit_transaction->t_handle_lock);
}
finish_wait(&journal->j_wait_updates, &wait);
}
spin_unlock(&commit_transaction->t_handle_lock);
- J_ASSERT (commit_transaction->t_outstanding_credits <=
+ J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <=
journal->j_max_transaction_buffers);
/*
@@ -486,9 +447,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
jbd2_journal_switch_revoke_table(journal);
trace_jbd2_commit_flushing(journal, commit_transaction);
- stats.u.run.rs_flushing = jiffies;
- stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
- stats.u.run.rs_flushing);
+ stats.run.rs_flushing = jiffies;
+ stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,
+ stats.run.rs_flushing);
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
@@ -496,7 +457,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
jbd_debug (3, "JBD: commit phase 2\n");
@@ -518,19 +479,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
* transaction! Now comes the tricky part: we need to write out
* metadata. Loop over the transaction's entire buffer list:
*/
- spin_lock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
commit_transaction->t_state = T_COMMIT;
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
trace_jbd2_commit_logging(journal, commit_transaction);
- stats.u.run.rs_logging = jiffies;
- stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
- stats.u.run.rs_logging);
- stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits;
- stats.u.run.rs_blocks_logged = 0;
+ stats.run.rs_logging = jiffies;
+ stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing,
+ stats.run.rs_logging);
+ stats.run.rs_blocks =
+ atomic_read(&commit_transaction->t_outstanding_credits);
+ stats.run.rs_blocks_logged = 0;
J_ASSERT(commit_transaction->t_nr_buffers <=
- commit_transaction->t_outstanding_credits);
+ atomic_read(&commit_transaction->t_outstanding_credits));
err = 0;
descriptor = NULL;
@@ -615,7 +577,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
* the free space in the log, but this counter is changed
* by jbd2_journal_next_log_block() also.
*/
- commit_transaction->t_outstanding_credits--;
+ atomic_dec(&commit_transaction->t_outstanding_credits);
/* Bump b_count to prevent truncate from stumbling over
the shadowed buffer! @@@ This can go if we ever get
@@ -636,6 +598,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
JBUFFER_TRACE(jh, "ph3: write metadata");
flags = jbd2_journal_write_metadata_buffer(commit_transaction,
jh, &new_jh, blocknr);
+ if (flags < 0) {
+ jbd2_journal_abort(journal, flags);
+ continue;
+ }
set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
wbuf[bufs++] = jh2bh(new_jh);
@@ -695,7 +661,7 @@ start_journal_io:
submit_bh(write_op, bh);
}
cond_resched();
- stats.u.run.rs_blocks_logged += bufs;
+ stats.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
@@ -704,23 +670,6 @@ start_journal_io:
}
}
- /* Done it all: now write the commit record asynchronously. */
-
- if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
- err = journal_submit_commit_record(journal, commit_transaction,
- &cbh, crc32_sum);
- if (err)
- __jbd2_journal_abort_hard(journal);
- }
-
- /*
- * This is the right place to wait for data buffers both for ASYNC
- * and !ASYNC commit. If commit is ASYNC, we need to wait only after
- * the commit block went to disk (which happens above). If commit is
- * SYNC, we need to wait for data buffers before we start writing
- * commit block, which happens below in such setting.
- */
err = journal_finish_inode_data_buffers(journal, commit_transaction);
if (err) {
printk(KERN_WARNING
@@ -731,6 +680,25 @@ start_journal_io:
err = 0;
}
+ /*
+ * If the journal is not located on the file system device,
+ * then we must flush the file system device before we issue
+ * the commit record
+ */
+ if (commit_transaction->t_flushed_data_blocks &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+
+ /* Done it all: now write the commit record asynchronously. */
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ err = journal_submit_commit_record(journal, commit_transaction,
+ &cbh, crc32_sum);
+ if (err)
+ __jbd2_journal_abort_hard(journal);
+ }
+
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
@@ -834,7 +802,7 @@ wait_for_iobuf:
jbd_debug(3, "JBD: commit phase 5\n");
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
@@ -842,6 +810,11 @@ wait_for_iobuf:
}
if (!err && !is_journal_aborted(journal))
err = journal_wait_on_commit_record(journal, cbh);
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
+ journal->j_flags & JBD2_BARRIER) {
+ blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL);
+ }
if (err)
jbd2_journal_abort(journal, err);
@@ -874,8 +847,7 @@ restart_loop:
spin_unlock(&journal->j_list_lock);
bh = jh2bh(jh);
jbd_lock_bh_state(bh);
- J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
- jh->b_transaction == journal->j_running_transaction);
+ J_ASSERT_JH(jh, jh->b_transaction == commit_transaction);
/*
* If there is undo-protected committed data against
@@ -921,12 +893,12 @@ restart_loop:
/* 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);
}
@@ -967,7 +939,7 @@ restart_loop:
* __jbd2_journal_drop_transaction(). Otherwise we could race with
* other checkpointing code processing the transaction...
*/
- spin_lock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
/*
* Now recheck if some buffers did not get attached to the transaction
@@ -975,7 +947,7 @@ restart_loop:
*/
if (commit_transaction->t_forget) {
spin_unlock(&journal->j_list_lock);
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
goto restart_loop;
}
@@ -986,33 +958,31 @@ restart_loop:
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_start = jiffies;
- stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging,
- commit_transaction->t_start);
+ stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,
+ commit_transaction->t_start);
/*
- * File the transaction for history
+ * File the transaction statistics
*/
- stats.ts_type = JBD2_STATS_RUN;
stats.ts_tid = commit_transaction->t_tid;
- stats.u.run.rs_handle_count = commit_transaction->t_handle_count;
- spin_lock(&journal->j_history_lock);
- memcpy(journal->j_history + journal->j_history_cur, &stats,
- sizeof(stats));
- if (++journal->j_history_cur == journal->j_history_max)
- journal->j_history_cur = 0;
+ stats.run.rs_handle_count =
+ atomic_read(&commit_transaction->t_handle_count);
+ trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
+ commit_transaction->t_tid, &stats.run);
/*
* Calculate overall stats
*/
+ spin_lock(&journal->j_history_lock);
journal->j_stats.ts_tid++;
- journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait;
- journal->j_stats.u.run.rs_running += stats.u.run.rs_running;
- journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked;
- journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing;
- journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging;
- journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count;
- journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks;
- journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged;
+ journal->j_stats.run.rs_wait += stats.run.rs_wait;
+ journal->j_stats.run.rs_running += stats.run.rs_running;
+ journal->j_stats.run.rs_locked += stats.run.rs_locked;
+ journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+ journal->j_stats.run.rs_logging += stats.run.rs_logging;
+ journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+ journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+ journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
spin_unlock(&journal->j_history_lock);
commit_transaction->t_state = T_FINISHED;
@@ -1030,7 +1000,7 @@ restart_loop:
journal->j_average_commit_time*3) / 4;
else
journal->j_average_commit_time = commit_time;
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
Powered by cgit, Gruvboxed by Blaster4385.