summaryrefslogtreecommitdiff
path: root/fs/jbd2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd2')
-rw-r--r--fs/jbd2/checkpoint.c17
-rw-r--r--fs/jbd2/commit.c6
-rw-r--r--fs/jbd2/journal.c90
-rw-r--r--fs/jbd2/transaction.c83
4 files changed, 119 insertions, 77 deletions
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 26f8d7e46462..02e0b79753e7 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -113,7 +113,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
nblocks = jbd2_space_needed(journal);
while (jbd2_log_space_left(journal) < nblocks) {
write_unlock(&journal->j_state_lock);
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
/*
* Test again, another process may have checkpointed while we
@@ -276,9 +276,22 @@ restart:
"JBD2: %s: Waiting for Godot: block %llu\n",
journal->j_devname, (unsigned long long) bh->b_blocknr);
+ if (batch_count)
+ __flush_batch(journal, &batch_count);
jbd2_log_start_commit(journal, tid);
+ /*
+ * jbd2_journal_commit_transaction() may want
+ * to take the checkpoint_mutex if JBD2_FLUSHED
+ * is set, jbd2_update_log_tail() called by
+ * jbd2_journal_commit_transaction() may also take
+ * checkpoint_mutex. So we need to temporarily
+ * drop it.
+ */
+ mutex_unlock(&journal->j_checkpoint_mutex);
jbd2_log_wait_commit(journal, tid);
- goto retry;
+ mutex_lock_io(&journal->j_checkpoint_mutex);
+ spin_lock(&journal->j_list_lock);
+ goto restart;
}
if (!buffer_dirty(bh)) {
if (unlikely(buffer_write_io_error(bh)) && !result)
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2eb55c3361a8..efd0ce9489ae 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -694,9 +694,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
the last tag we set up. */
tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG);
-
- jbd2_descriptor_block_csum_set(journal, descriptor);
start_journal_io:
+ if (descriptor)
+ jbd2_descriptor_block_csum_set(journal,
+ descriptor);
+
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
/*
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8ef6b6daaa7a..382c030cc78b 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -142,22 +142,6 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
return cpu_to_be32(csum);
}
-static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
-{
- if (!jbd2_journal_has_csum_v2or3(j))
- return 1;
-
- return sb->s_checksum == jbd2_superblock_csum(j, sb);
-}
-
-static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
-{
- if (!jbd2_journal_has_csum_v2or3(j))
- return;
-
- sb->s_checksum = jbd2_superblock_csum(j, sb);
-}
-
/*
* Helper function used to manage commit timeouts
*/
@@ -1356,6 +1340,10 @@ static int journal_reset(journal_t *journal)
return jbd2_journal_start_thread(journal);
}
+/*
+ * This function expects that the caller will have locked the journal
+ * buffer head, and will return with it unlocked
+ */
static int jbd2_write_superblock(journal_t *journal, int write_flags)
{
struct buffer_head *bh = journal->j_sb_buffer;
@@ -1365,7 +1353,6 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
trace_jbd2_write_superblock(journal, write_flags);
if (!(journal->j_flags & JBD2_BARRIER))
write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
- lock_buffer(bh);
if (buffer_write_io_error(bh)) {
/*
* Oh, dear. A previous attempt to write the journal
@@ -1381,7 +1368,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
}
- jbd2_superblock_csum_set(journal, sb);
+ if (jbd2_journal_has_csum_v2or3(journal))
+ sb->s_checksum = jbd2_superblock_csum(journal, sb);
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
@@ -1424,6 +1412,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
tail_block, tail_tid);
+ lock_buffer(journal->j_sb_buffer);
sb->s_sequence = cpu_to_be32(tail_tid);
sb->s_start = cpu_to_be32(tail_block);
@@ -1454,18 +1443,17 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
journal_superblock_t *sb = journal->j_superblock;
BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
- read_lock(&journal->j_state_lock);
- /* Is it already empty? */
- if (sb->s_start == 0) {
- read_unlock(&journal->j_state_lock);
+ lock_buffer(journal->j_sb_buffer);
+ if (sb->s_start == 0) { /* Is it already empty? */
+ unlock_buffer(journal->j_sb_buffer);
return;
}
+
jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
journal->j_tail_sequence);
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
sb->s_start = cpu_to_be32(0);
- read_unlock(&journal->j_state_lock);
jbd2_write_superblock(journal, write_op);
@@ -1488,9 +1476,8 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
journal_superblock_t *sb = journal->j_superblock;
int errcode;
- read_lock(&journal->j_state_lock);
+ lock_buffer(journal->j_sb_buffer);
errcode = journal->j_errno;
- read_unlock(&journal->j_state_lock);
if (errcode == -ESHUTDOWN)
errcode = 0;
jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
@@ -1595,17 +1582,18 @@ static int journal_get_superblock(journal_t *journal)
}
}
- /* Check superblock checksum */
- if (!jbd2_superblock_csum_verify(journal, sb)) {
- printk(KERN_ERR "JBD2: journal checksum error\n");
- err = -EFSBADCRC;
- goto out;
- }
+ if (jbd2_journal_has_csum_v2or3(journal)) {
+ /* Check superblock checksum */
+ if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) {
+ printk(KERN_ERR "JBD2: journal checksum error\n");
+ err = -EFSBADCRC;
+ goto out;
+ }
- /* Precompute checksum seed for all metadata */
- if (jbd2_journal_has_csum_v2or3(journal))
+ /* Precompute checksum seed for all metadata */
journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
sizeof(sb->s_uuid));
+ }
set_buffer_verified(bh);
@@ -1894,28 +1882,27 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
sb = journal->j_superblock;
+ /* Load the checksum driver if necessary */
+ if ((journal->j_chksum_driver == NULL) &&
+ INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+ journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
+ if (IS_ERR(journal->j_chksum_driver)) {
+ printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
+ journal->j_chksum_driver = NULL;
+ return 0;
+ }
+ /* Precompute checksum seed for all metadata */
+ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
+ sizeof(sb->s_uuid));
+ }
+
+ lock_buffer(journal->j_sb_buffer);
+
/* If enabling v3 checksums, update superblock */
if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
sb->s_feature_compat &=
~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
-
- /* Load the checksum driver */
- if (journal->j_chksum_driver == NULL) {
- journal->j_chksum_driver = crypto_alloc_shash("crc32c",
- 0, 0);
- if (IS_ERR(journal->j_chksum_driver)) {
- printk(KERN_ERR "JBD2: Cannot load crc32c "
- "driver.\n");
- journal->j_chksum_driver = NULL;
- return 0;
- }
-
- /* Precompute checksum seed for all metadata */
- journal->j_csum_seed = jbd2_chksum(journal, ~0,
- sb->s_uuid,
- sizeof(sb->s_uuid));
- }
}
/* If enabling v1 checksums, downgrade superblock */
@@ -1927,6 +1914,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
sb->s_feature_compat |= cpu_to_be32(compat);
sb->s_feature_ro_compat |= cpu_to_be32(ro);
sb->s_feature_incompat |= cpu_to_be32(incompat);
+ unlock_buffer(journal->j_sb_buffer);
return 1;
#undef COMPAT_FEATURE_ON
@@ -2067,7 +2055,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
err = jbd2_journal_skip_recovery(journal);
if (write) {
/* Lock to make assertions happy... */
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
mutex_unlock(&journal->j_checkpoint_mutex);
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index cc35537232f2..f940d31c2adc 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -63,7 +63,7 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
/*
* jbd2_get_transaction: obtain a new transaction_t object.
*
- * Simply allocate and initialise a new transaction. Create it in
+ * Simply initialise a new transaction. Initialize it in
* RUNNING state and add it to the current journal (which should not
* have an existing running transaction: we only make a new transaction
* once we have started to commit the old one).
@@ -75,8 +75,8 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
*
*/
-static transaction_t *
-jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
+static void jbd2_get_transaction(journal_t *journal,
+ transaction_t *transaction)
{
transaction->t_journal = journal;
transaction->t_state = T_RUNNING;
@@ -100,8 +100,6 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
transaction->t_max_wait = 0;
transaction->t_start = jiffies;
transaction->t_requested = 0;
-
- return transaction;
}
/*
@@ -1252,11 +1250,12 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
struct journal_head *jh;
char *committed_data = NULL;
- JBUFFER_TRACE(jh, "entry");
if (jbd2_write_access_granted(handle, bh, true))
return 0;
jh = jbd2_journal_add_journal_head(bh);
+ JBUFFER_TRACE(jh, "entry");
+
/*
* Do this first --- it can drop the journal lock, so we want to
* make sure that obtaining the committed_data is done
@@ -1367,15 +1366,17 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
if (is_handle_aborted(handle))
return -EROFS;
- if (!buffer_jbd(bh)) {
- ret = -EUCLEAN;
- goto out;
- }
+ if (!buffer_jbd(bh))
+ return -EUCLEAN;
+
/*
* We don't grab jh reference here since the buffer must be part
* of the running transaction.
*/
jh = bh2jh(bh);
+ jbd_debug(5, "journal_head %p\n", jh);
+ JBUFFER_TRACE(jh, "entry");
+
/*
* This and the following assertions are unreliable since we may see jh
* in inconsistent state unless we grab bh_state lock. But this is
@@ -1409,9 +1410,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
}
journal = transaction->t_journal;
- jbd_debug(5, "journal_head %p\n", jh);
- JBUFFER_TRACE(jh, "entry");
-
jbd_lock_bh_state(bh);
if (jh->b_modified == 0) {
@@ -1597,9 +1595,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
__jbd2_journal_unfile_buffer(jh);
if (!buffer_jbd(bh)) {
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
- __bforget(bh);
- goto drop;
+ goto not_jbd;
}
}
spin_unlock(&journal->j_list_lock);
@@ -1609,14 +1605,21 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
/* However, if the buffer is still owned by a prior
* (committing) transaction, we can't drop it yet... */
JBUFFER_TRACE(jh, "belongs to older transaction");
- /* ... but we CAN drop it from the new transaction if we
- * have also modified it since the original commit. */
+ /* ... but we CAN drop it from the new transaction through
+ * marking the buffer as freed and set j_next_transaction to
+ * the new transaction, so that not only the commit code
+ * knows it should clear dirty bits when it is done with the
+ * buffer, but also the buffer can be checkpointed only
+ * after the new transaction commits. */
- if (jh->b_next_transaction) {
- J_ASSERT(jh->b_next_transaction == transaction);
+ set_buffer_freed(bh);
+
+ if (!jh->b_next_transaction) {
spin_lock(&journal->j_list_lock);
- jh->b_next_transaction = NULL;
+ jh->b_next_transaction = transaction;
spin_unlock(&journal->j_list_lock);
+ } else {
+ J_ASSERT(jh->b_next_transaction == transaction);
/*
* only drop a reference if this transaction modified
@@ -1625,9 +1628,40 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
if (was_modified)
drop_reserve = 1;
}
+ } else {
+ /*
+ * Finally, if the buffer is not belongs to any
+ * transaction, we can just drop it now if it has no
+ * checkpoint.
+ */
+ spin_lock(&journal->j_list_lock);
+ if (!jh->b_cp_transaction) {
+ JBUFFER_TRACE(jh, "belongs to none transaction");
+ spin_unlock(&journal->j_list_lock);
+ goto not_jbd;
+ }
+
+ /*
+ * Otherwise, if the buffer has been written to disk,
+ * it is safe to remove the checkpoint and drop it.
+ */
+ if (!buffer_dirty(bh)) {
+ __jbd2_journal_remove_checkpoint(jh);
+ spin_unlock(&journal->j_list_lock);
+ goto not_jbd;
+ }
+
+ /*
+ * The buffer is still not written to disk, we should
+ * attach this buffer to current transaction so that the
+ * buffer can be checkpointed only after the current
+ * transaction commits.
+ */
+ clear_buffer_dirty(bh);
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
+ spin_unlock(&journal->j_list_lock);
}
-not_jbd:
jbd_unlock_bh_state(bh);
__brelse(bh);
drop:
@@ -1636,6 +1670,11 @@ drop:
handle->h_buffer_credits++;
}
return err;
+
+not_jbd:
+ jbd_unlock_bh_state(bh);
+ __bforget(bh);
+ goto drop;
}
/**
generated by cgit (git 2.34.1) at 2024-06-20 14:01:27 +0000