/*
- * linux/fs/jbd/commit.c
+ * linux/fs/jbd2/commit.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
*
#include <linux/time.h>
#include <linux/fs.h>
-#include <linux/jbd.h>
+#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
+#include <linux/jiffies.h>
+#include <linux/crc32.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <trace/events/jbd2.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
}
/*
- * When an ext3-ordered file is truncated, it is possible that many pages are
- * not sucessfully freed, because they are attached to a committing transaction.
+ * When an ext4 file is truncated, it is possible that some pages are not
+ * successfully freed, because they are attached to a committing transaction.
* After the transaction commits, these pages are left on the LRU, with no
* ->mapping, and with attached buffers. These pages are trivially reclaimable
* by the VM, but their apparent absence upsets the VM accounting, and it makes
goto nope;
/* OK, it's a truncated page */
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto nope;
page_cache_get(page);
}
/*
- * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
- * held. For ranking reasons we must trylock. If we lose, schedule away and
- * return 0. j_list_lock is dropped in this case.
- */
-static int inverted_lock(journal_t *journal, struct buffer_head *bh)
-{
- if (!jbd_trylock_bh_state(bh)) {
- spin_unlock(&journal->j_list_lock);
- schedule();
- return 0;
- }
- return 1;
-}
-
-/* Done it all: now write the commit record. We should have
+ * Done it all: now submit the commit record. We should have
* cleaned up our previous buffers by now, so if we are in abort
* mode we can now just skip the rest of the journal write
* entirely.
*
* Returns 1 if the journal needs to be aborted or 0 on success
*/
-static int journal_write_commit_record(journal_t *journal,
- transaction_t *commit_transaction)
+static int journal_submit_commit_record(journal_t *journal,
+ transaction_t *commit_transaction,
+ struct buffer_head **cbh,
+ __u32 crc32_sum)
{
struct journal_head *descriptor;
+ struct commit_header *tmp;
struct buffer_head *bh;
- int i, ret;
+ int ret;
int barrier_done = 0;
+ struct timespec now = current_kernel_time();
if (is_journal_aborted(journal))
return 0;
- descriptor = journal_get_descriptor_buffer(journal);
+ descriptor = jbd2_journal_get_descriptor_buffer(journal);
if (!descriptor)
return 1;
bh = jh2bh(descriptor);
- /* AKPM: buglet - add `i' to tmp! */
- for (i = 0; i < bh->b_size; i += 512) {
- journal_header_t *tmp = (journal_header_t*)bh->b_data;
- tmp->h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
- tmp->h_blocktype = cpu_to_be32(JFS_COMMIT_BLOCK);
- tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+ tmp = (struct commit_header *)bh->b_data;
+ tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
+ tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+ tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
+ tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
+
+ if (JBD2_HAS_COMPAT_FEATURE(journal,
+ JBD2_FEATURE_COMPAT_CHECKSUM)) {
+ tmp->h_chksum_type = JBD2_CRC32_CHKSUM;
+ tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE;
+ tmp->h_chksum[0] = cpu_to_be32(crc32_sum);
}
- JBUFFER_TRACE(descriptor, "write commit block");
- set_buffer_dirty(bh);
- if (journal->j_flags & JFS_BARRIER) {
+ JBUFFER_TRACE(descriptor, "submit commit block");
+ lock_buffer(bh);
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ 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 = sync_dirty_buffer(bh);
+ 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) {
- 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 &= ~JFS_BARRIER;
+ journal->j_flags &= ~JBD2_BARRIER;
spin_unlock(&journal->j_state_lock);
/* And try again, without the barrier */
- clear_buffer_ordered(bh);
+ lock_buffer(bh);
set_buffer_uptodate(bh);
- set_buffer_dirty(bh);
- ret = sync_dirty_buffer(bh);
+ clear_buffer_dirty(bh);
+ ret = submit_bh(WRITE_SYNC_PLUG, bh);
}
- put_bh(bh); /* One for getblk() */
- journal_put_journal_head(descriptor);
-
- return (ret == -EIO);
+ *cbh = bh;
+ return ret;
}
-static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
+/*
+ * This function along with journal_submit_commit_record
+ * allows to write the commit record asynchronously.
+ */
+static int journal_wait_on_commit_record(journal_t *journal,
+ struct buffer_head *bh)
{
- int i;
+ 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);
- 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]);
+ 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;
+ put_bh(bh); /* One for getblk() */
+ jbd2_journal_put_journal_head(bh2jh(bh));
+
+ return ret;
}
/*
- * Submit all the data buffers to disk
+ * write the filemap data using writepage() address_space_operations.
+ * We don't do block allocation here even for delalloc. We don't
+ * use writepages() because with dealyed allocation we may be doing
+ * block allocation in writepages().
*/
-static void journal_submit_data_buffers(journal_t *journal,
- transaction_t *commit_transaction)
+static int journal_submit_inode_data_buffers(struct address_space *mapping)
{
- struct journal_head *jh;
- struct buffer_head *bh;
- int locked;
- int bufs = 0;
- struct buffer_head **wbuf = journal->j_wbuf;
+ int ret;
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = mapping->nrpages * 2,
+ .range_start = 0,
+ .range_end = i_size_read(mapping->host),
+ };
+
+ ret = generic_writepages(mapping, &wbc);
+ return ret;
+}
- /*
- * Whenever we unlock the journal and sleep, things can get added
- * onto ->t_sync_datalist, so we have to keep looping back to
- * write_out_data until we *know* that the list is empty.
- *
- * Cleanup any flushed data buffers from the data list. Even in
- * abort mode, we want to flush this out as soon as possible.
- */
-write_out_data:
- cond_resched();
- spin_lock(&journal->j_list_lock);
+/*
+ * Submit all the data buffers of inode associated with the transaction to
+ * disk.
+ *
+ * We are in a committing transaction. Therefore no new inode can be added to
+ * our inode list. We use JI_COMMIT_RUNNING flag to protect inode we currently
+ * operate on from being released while we write out pages.
+ */
+static int journal_submit_data_buffers(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct jbd2_inode *jinode;
+ int err, ret = 0;
+ struct address_space *mapping;
- while (commit_transaction->t_sync_datalist) {
- jh = commit_transaction->t_sync_datalist;
- bh = jh2bh(jh);
- locked = 0;
-
- /* Get reference just to make sure buffer does not disappear
- * when we are forced to drop various locks */
- get_bh(bh);
- /* If the buffer is dirty, we need to submit IO and hence
- * we need the buffer lock. We try to lock the buffer without
- * blocking. If we fail, we need to drop j_list_lock and do
- * blocking lock_buffer().
+ 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;
+ spin_unlock(&journal->j_list_lock);
+ /*
+ * submit the inode data buffers. We use writepage
+ * instead of writepages. Because writepages can do
+ * block allocation with delalloc. We need to write
+ * only allocated blocks here.
*/
- if (buffer_dirty(bh)) {
- if (test_set_buffer_locked(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);
- bufs = 0;
- lock_buffer(bh);
- spin_lock(&journal->j_list_lock);
- }
- locked = 1;
- }
- /* We have to get bh_state lock. Again out of order, sigh. */
- if (!inverted_lock(journal, bh)) {
- jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
- }
- /* Someone already cleaned up the buffer? */
- if (!buffer_jbd(bh)
- || jh->b_transaction != commit_transaction
- || jh->b_jlist != BJ_SyncData) {
- jbd_unlock_bh_state(bh);
- if (locked)
- unlock_buffer(bh);
- BUFFER_TRACE(bh, "already cleaned up");
- put_bh(bh);
- continue;
- }
- if (locked && test_clear_buffer_dirty(bh)) {
- BUFFER_TRACE(bh, "needs writeout, adding to array");
- wbuf[bufs++] = bh;
- __journal_file_buffer(jh, commit_transaction,
- BJ_Locked);
- jbd_unlock_bh_state(bh);
- if (bufs == journal->j_wbufsize) {
- spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
- bufs = 0;
- goto write_out_data;
- }
- }
- else {
- BUFFER_TRACE(bh, "writeout complete: unfile");
- __journal_unfile_buffer(jh);
- jbd_unlock_bh_state(bh);
- if (locked)
- unlock_buffer(bh);
- journal_remove_journal_head(bh);
- /* Once for our safety reference, once for
- * journal_remove_journal_head() */
- put_bh(bh);
- put_bh(bh);
+ trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+ err = journal_submit_inode_data_buffers(mapping);
+ if (!ret)
+ ret = err;
+ spin_lock(&journal->j_list_lock);
+ J_ASSERT(jinode->i_transaction == commit_transaction);
+ jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ }
+ spin_unlock(&journal->j_list_lock);
+ return ret;
+}
+
+/*
+ * Wait for data submitted for writeout, refile inodes to proper
+ * transaction if needed.
+ *
+ */
+static int journal_finish_inode_data_buffers(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct jbd2_inode *jinode, *next_i;
+ int err, ret = 0;
+
+ /* 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;
+ 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
+ * that user process can get -EIO from fsync().
+ */
+ set_bit(AS_EIO,
+ &jinode->i_vfs_inode->i_mapping->flags);
+
+ if (!ret)
+ ret = err;
}
+ spin_lock(&journal->j_list_lock);
+ jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ }
- if (lock_need_resched(&journal->j_list_lock)) {
- spin_unlock(&journal->j_list_lock);
- goto write_out_data;
+ /* Now refile inode to proper lists */
+ list_for_each_entry_safe(jinode, next_i,
+ &commit_transaction->t_inode_list, i_list) {
+ list_del(&jinode->i_list);
+ if (jinode->i_next_transaction) {
+ jinode->i_transaction = jinode->i_next_transaction;
+ jinode->i_next_transaction = NULL;
+ list_add(&jinode->i_list,
+ &jinode->i_transaction->t_inode_list);
+ } else {
+ jinode->i_transaction = NULL;
}
}
spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
+
+ return ret;
+}
+
+static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
+{
+ struct page *page = bh->b_page;
+ char *addr;
+ __u32 checksum;
+
+ addr = kmap_atomic(page, KM_USER0);
+ checksum = crc32_be(crc32_sum,
+ (void *)(addr + offset_in_page(bh->b_data)), bh->b_size);
+ kunmap_atomic(addr, KM_USER0);
+
+ return checksum;
+}
+
+static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+ unsigned long long block)
+{
+ tag->t_blocknr = cpu_to_be32(block & (u32)~0);
+ if (tag_bytes > JBD2_TAG_SIZE32)
+ tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
}
/*
- * journal_commit_transaction
+ * jbd2_journal_commit_transaction
*
* The primary function for committing a transaction to the log. This
* function is called by the journal thread to begin a complete commit.
*/
-void journal_commit_transaction(journal_t *journal)
+void jbd2_journal_commit_transaction(journal_t *journal)
{
+ struct transaction_stats_s stats;
transaction_t *commit_transaction;
struct journal_head *jh, *new_jh, *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
int flags;
int err;
- unsigned long blocknr;
+ unsigned long long blocknr;
+ ktime_t start_time;
+ u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
int space_left = 0;
int first_tag = 0;
int tag_flag;
- int i;
+ int i, to_free = 0;
+ 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
spin_unlock(&journal->j_list_lock);
#endif
- /* Do we need to erase the effects of a prior journal_flush? */
- if (journal->j_flags & JFS_FLUSHED) {
+ /* Do we need to erase the effects of a prior jbd2_journal_flush? */
+ if (journal->j_flags & JBD2_FLUSHED) {
jbd_debug(3, "super block updated\n");
- journal_update_superblock(journal, 1);
+ jbd2_journal_update_superblock(journal, 1);
} else {
jbd_debug(3, "superblock not updated\n");
}
commit_transaction = journal->j_running_transaction;
J_ASSERT(commit_transaction->t_state == T_RUNNING);
+ trace_jbd2_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD: starting commit of transaction %d\n",
commit_transaction->t_tid);
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;
+ trace_jbd2_commit_locking(journal, commit_transaction);
+ 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) {
DEFINE_WAIT(wait);
* BJ_Reserved buffers. Note, it is _not_ permissible to assume
* that there are no such buffers: if a large filesystem
* operation like a truncate needs to split itself over multiple
- * transactions, then it may try to do a journal_restart() while
+ * transactions, then it may try to do a jbd2_journal_restart() while
* there are still BJ_Reserved buffers outstanding. These must
* be released cleanly from the current transaction.
*
* again before modifying the buffer in the new transaction, but
* we do not require it to remember exactly which old buffers it
* has reserved. This is consistent with the existing behaviour
- * that multiple journal_get_write_access() calls to the same
+ * that multiple jbd2_journal_get_write_access() calls to the same
* buffer are perfectly permissable.
*/
while (commit_transaction->t_reserved_list) {
jh = commit_transaction->t_reserved_list;
JBUFFER_TRACE(jh, "reserved, unused: refile");
/*
- * A journal_get_undo_access()+journal_release_buffer() may
+ * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may
* leave undo-committed data.
*/
if (jh->b_committed_data) {
struct buffer_head *bh = jh2bh(jh);
jbd_lock_bh_state(bh);
- jbd_slab_free(jh->b_committed_data, bh->b_size);
+ jbd2_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
jbd_unlock_bh_state(bh);
}
- journal_refile_buffer(journal, jh);
+ jbd2_journal_refile_buffer(journal, jh);
}
/*
* frees some memory
*/
spin_lock(&journal->j_list_lock);
- __journal_clean_checkpoint_list(journal);
+ __jbd2_journal_clean_checkpoint_list(journal);
spin_unlock(&journal->j_list_lock);
jbd_debug (3, "JBD: commit phase 1\n");
/*
* Switch to a new revoke table.
*/
- journal_switch_revoke_table(journal);
+ jbd2_journal_switch_revoke_table(journal);
+
+ trace_jbd2_commit_flushing(journal, commit_transaction);
+ 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;
journal->j_running_transaction = NULL;
+ 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);
jbd_debug (3, "JBD: commit phase 2\n");
/*
- * First, drop modified flag: all accesses to the buffers
- * will be tracked for a new trasaction only -bzzz
- */
- spin_lock(&journal->j_list_lock);
- if (commit_transaction->t_buffers) {
- new_jh = jh = commit_transaction->t_buffers->b_tnext;
- do {
- J_ASSERT_JH(new_jh, new_jh->b_modified == 1 ||
- new_jh->b_modified == 0);
- new_jh->b_modified = 0;
- new_jh = new_jh->b_tnext;
- } while (new_jh != jh);
- }
- spin_unlock(&journal->j_list_lock);
-
- /*
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
- err = 0;
- journal_submit_data_buffers(journal, commit_transaction);
-
- /*
- * Wait for all previously submitted IO to complete.
- */
- spin_lock(&journal->j_list_lock);
- while (commit_transaction->t_locked_list) {
- struct buffer_head *bh;
-
- jh = commit_transaction->t_locked_list->b_tprev;
- bh = jh2bh(jh);
- get_bh(bh);
- if (buffer_locked(bh)) {
- spin_unlock(&journal->j_list_lock);
- wait_on_buffer(bh);
- if (unlikely(!buffer_uptodate(bh)))
- err = -EIO;
- spin_lock(&journal->j_list_lock);
- }
- if (!inverted_lock(journal, bh)) {
- put_bh(bh);
- spin_lock(&journal->j_list_lock);
- continue;
- }
- if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
- __journal_unfile_buffer(jh);
- jbd_unlock_bh_state(bh);
- journal_remove_journal_head(bh);
- put_bh(bh);
- } else {
- jbd_unlock_bh_state(bh);
- }
- put_bh(bh);
- cond_resched_lock(&journal->j_list_lock);
- }
- spin_unlock(&journal->j_list_lock);
-
+ err = journal_submit_data_buffers(journal, commit_transaction);
if (err)
- __journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
- journal_write_revoke_records(journal, commit_transaction);
+ jbd2_journal_write_revoke_records(journal, commit_transaction,
+ write_op);
jbd_debug(3, "JBD: commit phase 2\n");
/*
- * If we found any dirty or locked buffers, then we should have
- * looped back up to the write_out_data label. If there weren't
- * any then journal_clean_data_list should have wiped the list
- * clean by now, so check that it is in fact empty.
- */
- J_ASSERT (commit_transaction->t_sync_datalist == NULL);
-
- jbd_debug (3, "JBD: commit phase 3\n");
-
- /*
* Way to go: we have now written out all of the data for a
* 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);
commit_transaction->t_state = T_COMMIT;
+ spin_unlock(&journal->j_state_lock);
+
+ trace_jbd2_commit_logging(journal, commit_transaction);
+ stats.run.rs_logging = jiffies;
+ stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing,
+ stats.run.rs_logging);
+ stats.run.rs_blocks = commit_transaction->t_outstanding_credits;
+ stats.run.rs_blocks_logged = 0;
+
+ J_ASSERT(commit_transaction->t_nr_buffers <=
+ commit_transaction->t_outstanding_credits);
+ err = 0;
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
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");
- journal_refile_buffer(journal, jh);
+ jbd2_buffer_abort_trigger(jh,
+ jh->b_frozen_data ?
+ jh->b_frozen_triggers :
+ jh->b_triggers);
+ jbd2_journal_refile_buffer(journal, jh);
/* If that was the last one, we need to clean up
* any descriptor buffers which may have been
* already allocated, even if we are now
jbd_debug(4, "JBD: get descriptor\n");
- descriptor = journal_get_descriptor_buffer(journal);
+ descriptor = jbd2_journal_get_descriptor_buffer(journal);
if (!descriptor) {
- __journal_abort_hard(journal);
+ jbd2_journal_abort(journal, -EIO);
continue;
}
jbd_debug(4, "JBD: got buffer %llu (%p)\n",
(unsigned long long)bh->b_blocknr, bh->b_data);
header = (journal_header_t *)&bh->b_data[0];
- header->h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
- header->h_blocktype = cpu_to_be32(JFS_DESCRIPTOR_BLOCK);
+ header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
tagp = &bh->b_data[sizeof(journal_header_t)];
/* Record it so that we can wait for IO
completion later */
BUFFER_TRACE(bh, "ph3: file as descriptor");
- journal_file_buffer(descriptor, commit_transaction,
+ jbd2_journal_file_buffer(descriptor, commit_transaction,
BJ_LogCtl);
}
/* Where is the buffer to be written? */
- err = journal_next_log_block(journal, &blocknr);
+ err = jbd2_journal_next_log_block(journal, &blocknr);
/* If the block mapping failed, just abandon the buffer
and repeat this loop: we'll fall into the
refile-on-abort condition above. */
if (err) {
- __journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
continue;
}
/*
* start_this_handle() uses t_outstanding_credits to determine
* the free space in the log, but this counter is changed
- * by journal_next_log_block() also.
+ * by jbd2_journal_next_log_block() also.
*/
commit_transaction->t_outstanding_credits--;
set_bit(BH_JWrite, &jh2bh(jh)->b_state);
/*
- * akpm: journal_write_metadata_buffer() sets
+ * akpm: jbd2_journal_write_metadata_buffer() sets
* new_bh->b_transaction to commit_transaction.
* We need to clean this up before we release new_bh
* (which is of type BJ_IO)
*/
JBUFFER_TRACE(jh, "ph3: write metadata");
- flags = journal_write_metadata_buffer(commit_transaction,
+ flags = jbd2_journal_write_metadata_buffer(commit_transaction,
jh, &new_jh, blocknr);
set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
wbuf[bufs++] = jh2bh(new_jh);
tag_flag = 0;
if (flags & 1)
- tag_flag |= JFS_FLAG_ESCAPE;
+ tag_flag |= JBD2_FLAG_ESCAPE;
if (!first_tag)
- tag_flag |= JFS_FLAG_SAME_UUID;
+ tag_flag |= JBD2_FLAG_SAME_UUID;
tag = (journal_block_tag_t *) tagp;
- tag->t_blocknr = cpu_to_be32(jh2bh(jh)->b_blocknr);
+ write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
tag->t_flags = cpu_to_be32(tag_flag);
- tagp += sizeof(journal_block_tag_t);
- space_left -= sizeof(journal_block_tag_t);
+ tagp += tag_bytes;
+ space_left -= tag_bytes;
if (first_tag) {
memcpy (tagp, journal->j_uuid, 16);
if (bufs == journal->j_wbufsize ||
commit_transaction->t_buffers == NULL ||
- space_left < sizeof(journal_block_tag_t) + 16) {
+ space_left < tag_bytes + 16) {
jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
submitting the IOs. "tag" still points to
the last tag we set up. */
- tag->t_flags |= cpu_to_be32(JFS_FLAG_LAST_TAG);
+ tag->t_flags |= cpu_to_be32(JBD2_FLAG_LAST_TAG);
start_journal_io:
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
+ /*
+ * Compute checksum.
+ */
+ if (JBD2_HAS_COMPAT_FEATURE(journal,
+ JBD2_FEATURE_COMPAT_CHECKSUM)) {
+ crc32_sum =
+ jbd2_checksum_data(crc32_sum, bh);
+ }
+
lock_buffer(bh);
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.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
}
}
+ /* 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);
+ if (journal->j_flags & JBD2_BARRIER)
+ blkdev_issue_flush(journal->j_dev, NULL);
+ }
+
+ /*
+ * 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
+ "JBD2: Detected IO errors while flushing file data "
+ "on %s\n", journal->j_devname);
+ if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR)
+ jbd2_journal_abort(journal, err);
+ err = 0;
+ }
+
/* 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
so we incur less scheduling load.
*/
- jbd_debug(3, "JBD: commit phase 4\n");
+ jbd_debug(3, "JBD: commit phase 3\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
clear_buffer_jwrite(bh);
JBUFFER_TRACE(jh, "ph4: unfile after journal write");
- journal_unfile_buffer(journal, jh);
+ jbd2_journal_unfile_buffer(journal, jh);
/*
* ->t_iobuf_list should contain only dummy buffer_heads
- * which were created by journal_write_metadata_buffer().
+ * which were created by jbd2_journal_write_metadata_buffer().
*/
BUFFER_TRACE(bh, "dumping temporary bh");
- journal_put_journal_head(jh);
+ jbd2_journal_put_journal_head(jh);
__brelse(bh);
J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
free_buffer_head(bh);
we finally commit, we can do any checkpointing
required. */
JBUFFER_TRACE(jh, "file as BJ_Forget");
- journal_file_buffer(jh, commit_transaction, BJ_Forget);
+ jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
/* Wake up any transactions which were waiting for this
IO to complete */
wake_up_bit(&bh->b_state, BH_Unshadow);
J_ASSERT (commit_transaction->t_shadow_list == NULL);
- jbd_debug(3, "JBD: commit phase 5\n");
+ jbd_debug(3, "JBD: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
- journal_unfile_buffer(journal, jh);
- journal_put_journal_head(jh);
+ jbd2_journal_unfile_buffer(journal, jh);
+ jbd2_journal_put_journal_head(jh);
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
- jbd_debug(3, "JBD: commit phase 6\n");
+ if (err)
+ jbd2_journal_abort(journal, err);
- if (journal_write_commit_record(journal, commit_transaction))
- err = -EIO;
+ jbd_debug(3, "JBD: commit phase 5\n");
+
+ 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);
+ }
+ if (!err && !is_journal_aborted(journal))
+ err = journal_wait_on_commit_record(journal, cbh);
if (err)
- __journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
/* End of a transaction! Finally, we can do checkpoint
processing: any buffers committed as a result of this
transaction can be removed from any checkpoint list it was on
before. */
- jbd_debug(3, "JBD: commit phase 7\n");
+ jbd_debug(3, "JBD: commit phase 6\n");
- J_ASSERT(commit_transaction->t_sync_datalist == NULL);
+ J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
J_ASSERT(commit_transaction->t_iobuf_list == NULL);
* data.
*
* Otherwise, we can just throw away the frozen data now.
+ *
+ * We also know that the frozen data has already fired
+ * its triggers if they exist, so we can clear that too.
*/
if (jh->b_committed_data) {
- jbd_slab_free(jh->b_committed_data, bh->b_size);
+ jbd2_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
if (jh->b_frozen_data) {
jh->b_committed_data = jh->b_frozen_data;
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
} else if (jh->b_frozen_data) {
- jbd_slab_free(jh->b_frozen_data, bh->b_size);
+ jbd2_free(jh->b_frozen_data, bh->b_size);
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
spin_lock(&journal->j_list_lock);
cp_transaction = jh->b_cp_transaction;
if (cp_transaction) {
JBUFFER_TRACE(jh, "remove from old cp transaction");
- __journal_remove_checkpoint(jh);
+ cp_transaction->t_chp_stats.cs_dropped++;
+ __jbd2_journal_remove_checkpoint(jh);
}
/* Only re-checkpoint the buffer_head if it is marked
* dirty. If the buffer was added to the BJ_Forget list
- * by journal_forget, it may no longer be dirty and
+ * by jbd2_journal_forget, it may no longer be dirty and
* there's no point in keeping a checkpoint record for
* it. */
if (buffer_jbddirty(bh)) {
JBUFFER_TRACE(jh, "add to new checkpointing trans");
- __journal_insert_checkpoint(jh, commit_transaction);
+ __jbd2_journal_insert_checkpoint(jh, commit_transaction);
+ if (is_journal_aborted(journal))
+ clear_buffer_jbddirty(bh);
JBUFFER_TRACE(jh, "refile for checkpoint writeback");
- __journal_refile_buffer(jh);
+ __jbd2_journal_refile_buffer(jh);
jbd_unlock_bh_state(bh);
} else {
J_ASSERT_BH(bh, !buffer_dirty(bh));
* disk and before we process the buffer on BJ_Forget
* list. */
JBUFFER_TRACE(jh, "refile or unfile freed buffer");
- __journal_refile_buffer(jh);
+ __jbd2_journal_refile_buffer(jh);
if (!jh->b_transaction) {
jbd_unlock_bh_state(bh);
/* needs a brelse */
- journal_remove_journal_head(bh);
+ jbd2_journal_remove_journal_head(bh);
release_buffer_page(bh);
} else
jbd_unlock_bh_state(bh);
}
spin_unlock(&journal->j_list_lock);
/*
- * This is a bit sleazy. We borrow j_list_lock to protect
- * journal->j_committing_transaction in __journal_remove_checkpoint.
- * Really, __journal_remove_checkpoint should be using j_state_lock but
- * it's a bit hassle to hold that across __journal_remove_checkpoint
+ * This is a bit sleazy. We use j_list_lock to protect transition
+ * of a transaction into T_FINISHED state and calling
+ * __jbd2_journal_drop_transaction(). Otherwise we could race with
+ * other checkpointing code processing the transaction...
*/
spin_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
/* Done with this transaction! */
- jbd_debug(3, "JBD: commit phase 8\n");
+ jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT);
+ commit_transaction->t_start = jiffies;
+ stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,
+ commit_transaction->t_start);
+
+ /*
+ * File the transaction statistics
+ */
+ stats.ts_tid = commit_transaction->t_tid;
+ stats.run.rs_handle_count = 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.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;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
+ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+
+ /*
+ * weight the commit time higher than the average time so we don't
+ * react too strongly to vast changes in the commit time
+ */
+ if (likely(journal->j_average_commit_time))
+ journal->j_average_commit_time = (commit_time +
+ journal->j_average_commit_time*3) / 4;
+ else
+ journal->j_average_commit_time = commit_time;
spin_unlock(&journal->j_state_lock);
- if (commit_transaction->t_checkpoint_list == NULL) {
- __journal_drop_transaction(journal, commit_transaction);
+ if (commit_transaction->t_checkpoint_list == NULL &&
+ commit_transaction->t_checkpoint_io_list == NULL) {
+ __jbd2_journal_drop_transaction(journal, commit_transaction);
+ to_free = 1;
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
}
spin_unlock(&journal->j_list_lock);
+ if (journal->j_commit_callback)
+ journal->j_commit_callback(journal, commit_transaction);
+
+ trace_jbd2_end_commit(journal, commit_transaction);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
+ if (to_free)
+ kfree(commit_transaction);
wake_up(&journal->j_wait_done_commit);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff