summaryrefslogtreecommitdiff
path: root/fs/jbd2/transaction.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd2/transaction.c')
-rw-r--r--fs/jbd2/transaction.c409
1 files changed, 203 insertions, 206 deletions
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6a3caedd2285..dca4b5d8aaaa 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -63,28 +63,6 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
}
/*
- * Base amount of descriptor blocks we reserve for each transaction.
- */
-static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
-{
- int tag_space = journal->j_blocksize - sizeof(journal_header_t);
- int tags_per_block;
-
- /* Subtract UUID */
- tag_space -= 16;
- if (jbd2_journal_has_csum_v2or3(journal))
- tag_space -= sizeof(struct jbd2_journal_block_tail);
- /* Commit code leaves a slack space of 16 bytes at the end of block */
- tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
- /*
- * Revoke descriptors are accounted separately so we need to reserve
- * space for commit block and normal transaction descriptor blocks.
- */
- return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers,
- tags_per_block);
-}
-
-/*
* jbd2_get_transaction: obtain a new transaction_t object.
*
* Simply initialise a new transaction. Initialize it in
@@ -107,15 +85,13 @@ static void jbd2_get_transaction(journal_t *journal,
transaction->t_start_time = ktime_get();
transaction->t_tid = journal->j_transaction_sequence++;
transaction->t_expires = jiffies + journal->j_commit_interval;
- spin_lock_init(&transaction->t_handle_lock);
atomic_set(&transaction->t_updates, 0);
atomic_set(&transaction->t_outstanding_credits,
- jbd2_descriptor_blocks_per_trans(journal) +
+ journal->j_transaction_overhead_buffers +
atomic_read(&journal->j_reserved_credits));
atomic_set(&transaction->t_outstanding_revokes, 0);
atomic_set(&transaction->t_handle_count, 0);
INIT_LIST_HEAD(&transaction->t_inode_list);
- INIT_LIST_HEAD(&transaction->t_private_list);
/* Set up the commit timer for the new transaction. */
journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires);
@@ -137,28 +113,21 @@ static void jbd2_get_transaction(journal_t *journal,
*/
/*
- * Update transaction's maximum wait time, if debugging is enabled.
- *
- * In order for t_max_wait to be reliable, it must be protected by a
- * lock. But doing so will mean that start_this_handle() can not be
- * run in parallel on SMP systems, which limits our scalability. So
- * unless debugging is enabled, we no longer update t_max_wait, which
- * means that maximum wait time reported by the jbd2_run_stats
- * tracepoint will always be zero.
+ * t_max_wait is carefully updated here with use of atomic compare exchange.
+ * Note that there could be multiplre threads trying to do this simultaneously
+ * hence using cmpxchg to avoid any use of locks in this case.
*/
static inline void update_t_max_wait(transaction_t *transaction,
unsigned long ts)
{
-#ifdef CONFIG_JBD2_DEBUG
- if (jbd2_journal_enable_debug &&
- time_after(transaction->t_start, ts)) {
- ts = jbd2_time_diff(ts, transaction->t_start);
- spin_lock(&transaction->t_handle_lock);
- if (ts > transaction->t_max_wait)
- transaction->t_max_wait = ts;
- spin_unlock(&transaction->t_handle_lock);
+ unsigned long oldts, newts;
+
+ if (time_after(transaction->t_start, ts)) {
+ newts = jbd2_time_diff(ts, transaction->t_start);
+ oldts = READ_ONCE(transaction->t_max_wait);
+ while (oldts < newts)
+ oldts = cmpxchg(&transaction->t_max_wait, oldts, newts);
}
-#endif
}
/*
@@ -173,7 +142,7 @@ static void wait_transaction_locked(journal_t *journal)
int need_to_start;
tid_t tid = journal->j_running_transaction->t_tid;
- prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
+ prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
@@ -199,7 +168,7 @@ static void wait_transaction_switching(journal_t *journal)
read_unlock(&journal->j_state_lock);
return;
}
- prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
+ prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
read_unlock(&journal->j_state_lock);
/*
@@ -218,6 +187,13 @@ static void sub_reserved_credits(journal_t *journal, int blocks)
wake_up(&journal->j_wait_reserved);
}
+/* Maximum number of blocks for user transaction payload */
+static int jbd2_max_user_trans_buffers(journal_t *journal)
+{
+ return journal->j_max_transaction_buffers -
+ journal->j_transaction_overhead_buffers;
+}
+
/*
* Wait until we can add credits for handle to the running transaction. Called
* with j_state_lock held for reading. Returns 0 if handle joined the running
@@ -267,12 +243,12 @@ __must_hold(&journal->j_state_lock)
* big to fit this handle? Wait until reserved credits are freed.
*/
if (atomic_read(&journal->j_reserved_credits) + total >
- journal->j_max_transaction_buffers) {
+ jbd2_max_user_trans_buffers(journal)) {
read_unlock(&journal->j_state_lock);
jbd2_might_wait_for_commit(journal);
wait_event(journal->j_wait_reserved,
atomic_read(&journal->j_reserved_credits) + total <=
- journal->j_max_transaction_buffers);
+ jbd2_max_user_trans_buffers(journal));
__acquire(&journal->j_state_lock); /* fake out sparse */
return 1;
}
@@ -312,14 +288,14 @@ __must_hold(&journal->j_state_lock)
needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits);
/* We allow at most half of a transaction to be reserved */
- if (needed > journal->j_max_transaction_buffers / 2) {
+ if (needed > jbd2_max_user_trans_buffers(journal) / 2) {
sub_reserved_credits(journal, rsv_blocks);
atomic_sub(total, &t->t_outstanding_credits);
read_unlock(&journal->j_state_lock);
jbd2_might_wait_for_commit(journal);
wait_event(journal->j_wait_reserved,
atomic_read(&journal->j_reserved_credits) + rsv_blocks
- <= journal->j_max_transaction_buffers / 2);
+ <= jbd2_max_user_trans_buffers(journal) / 2);
__acquire(&journal->j_state_lock); /* fake out sparse */
return 1;
}
@@ -349,12 +325,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
* size and limit the number of total credits to not exceed maximum
* transaction size per operation.
*/
- if ((rsv_blocks > journal->j_max_transaction_buffers / 2) ||
- (rsv_blocks + blocks > journal->j_max_transaction_buffers)) {
+ if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 ||
+ rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) {
printk(KERN_ERR "JBD2: %s wants too many credits "
"credits:%d rsv_credits:%d max:%d\n",
current->comm, blocks, rsv_blocks,
- journal->j_max_transaction_buffers);
+ jbd2_max_user_trans_buffers(journal));
WARN_ON(1);
return -ENOSPC;
}
@@ -378,7 +354,7 @@ alloc_transaction:
return -ENOMEM;
}
- jbd_debug(3, "New handle %p going live.\n", handle);
+ jbd2_debug(3, "New handle %p going live.\n", handle);
/*
* We need to hold j_state_lock until t_updates has been incremented,
@@ -449,7 +425,7 @@ repeat:
}
/* OK, account for the buffers that this operation expects to
- * use and add the handle to the running transaction.
+ * use and add the handle to the running transaction.
*/
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
@@ -458,14 +434,14 @@ repeat:
handle->h_start_jiffies = jiffies;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
- jbd_debug(4, "Handle %p given %d credits (total %d, free %lu)\n",
+ jbd2_debug(4, "Handle %p given %d credits (total %d, free %lu)\n",
handle, blocks,
atomic_read(&transaction->t_outstanding_credits),
jbd2_log_space_left(journal));
read_unlock(&journal->j_state_lock);
current->journal_info = handle;
- rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
+ rwsem_acquire_read(&journal->j_trans_commit_map, 0, 1, _THIS_IP_);
jbd2_journal_free_transaction(new_transaction);
/*
* Ensure that no allocations done while the transaction is open are
@@ -679,7 +655,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
/* Don't extend a locked-down transaction! */
if (transaction->t_state != T_RUNNING) {
- jbd_debug(3, "denied handle %p %d blocks: "
+ jbd2_debug(3, "denied handle %p %d blocks: "
"transaction not running\n", handle, nblocks);
goto error_out;
}
@@ -690,15 +666,14 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
DIV_ROUND_UP(
handle->h_revoke_credits_requested,
journal->j_revoke_records_per_block);
- spin_lock(&transaction->t_handle_lock);
wanted = atomic_add_return(nblocks,
&transaction->t_outstanding_credits);
if (wanted > journal->j_max_transaction_buffers) {
- jbd_debug(3, "denied handle %p %d blocks: "
+ jbd2_debug(3, "denied handle %p %d blocks: "
"transaction too large\n", handle, nblocks);
atomic_sub(nblocks, &transaction->t_outstanding_credits);
- goto unlock;
+ goto error_out;
}
trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
@@ -713,9 +688,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
handle->h_revoke_credits_requested += revoke_records;
result = 0;
- jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
-unlock:
- spin_unlock(&transaction->t_handle_lock);
+ jbd2_debug(3, "extended handle %p by %d\n", handle, nblocks);
error_out:
read_unlock(&journal->j_state_lock);
return result;
@@ -803,7 +776,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records,
* First unlink the handle from its current transaction, and start the
* commit on that.
*/
- jbd_debug(2, "restarting handle %p\n", handle);
+ jbd2_debug(2, "restarting handle %p\n", handle);
stop_this_handle(handle);
handle->h_transaction = NULL;
@@ -836,6 +809,43 @@ int jbd2_journal_restart(handle_t *handle, int nblocks)
}
EXPORT_SYMBOL(jbd2_journal_restart);
+/*
+ * Waits for any outstanding t_updates to finish.
+ * This is called with write j_state_lock held.
+ */
+void jbd2_journal_wait_updates(journal_t *journal)
+{
+ DEFINE_WAIT(wait);
+
+ while (1) {
+ /*
+ * Note that the running transaction can get freed under us if
+ * this transaction is getting committed in
+ * jbd2_journal_commit_transaction() ->
+ * jbd2_journal_free_transaction(). This can only happen when we
+ * release j_state_lock -> schedule() -> acquire j_state_lock.
+ * Hence we should everytime retrieve new j_running_transaction
+ * value (after j_state_lock release acquire cycle), else it may
+ * lead to use-after-free of old freed transaction.
+ */
+ transaction_t *transaction = journal->j_running_transaction;
+
+ if (!transaction)
+ break;
+
+ prepare_to_wait(&journal->j_wait_updates, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!atomic_read(&transaction->t_updates)) {
+ finish_wait(&journal->j_wait_updates, &wait);
+ break;
+ }
+ write_unlock(&journal->j_state_lock);
+ schedule();
+ finish_wait(&journal->j_wait_updates, &wait);
+ write_lock(&journal->j_state_lock);
+ }
+}
+
/**
* jbd2_journal_lock_updates () - establish a transaction barrier.
* @journal: Journal to establish a barrier on.
@@ -848,8 +858,6 @@ EXPORT_SYMBOL(jbd2_journal_restart);
*/
void jbd2_journal_lock_updates(journal_t *journal)
{
- DEFINE_WAIT(wait);
-
jbd2_might_wait_for_commit(journal);
write_lock(&journal->j_state_lock);
@@ -863,27 +871,9 @@ void jbd2_journal_lock_updates(journal_t *journal)
write_lock(&journal->j_state_lock);
}
- /* Wait until there are no running updates */
- while (1) {
- transaction_t *transaction = journal->j_running_transaction;
-
- if (!transaction)
- break;
+ /* Wait until there are no running t_updates */
+ jbd2_journal_wait_updates(journal);
- spin_lock(&transaction->t_handle_lock);
- prepare_to_wait(&journal->j_wait_updates, &wait,
- TASK_UNINTERRUPTIBLE);
- if (!atomic_read(&transaction->t_updates)) {
- spin_unlock(&transaction->t_handle_lock);
- finish_wait(&journal->j_wait_updates, &wait);
- break;
- }
- spin_unlock(&transaction->t_handle_lock);
- write_unlock(&journal->j_state_lock);
- schedule();
- finish_wait(&journal->j_wait_updates, &wait);
- write_lock(&journal->j_state_lock);
- }
write_unlock(&journal->j_state_lock);
/*
@@ -911,7 +901,7 @@ void jbd2_journal_unlock_updates (journal_t *journal)
write_lock(&journal->j_state_lock);
--journal->j_barrier_count;
write_unlock(&journal->j_state_lock);
- wake_up(&journal->j_wait_transaction_locked);
+ wake_up_all(&journal->j_wait_transaction_locked);
}
static void warn_dirty_buffer(struct buffer_head *bh)
@@ -926,19 +916,15 @@ static void warn_dirty_buffer(struct buffer_head *bh)
/* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */
static void jbd2_freeze_jh_data(struct journal_head *jh)
{
- struct page *page;
- int offset;
char *source;
struct buffer_head *bh = jh2bh(jh);
J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n");
- page = bh->b_page;
- offset = offset_in_page(bh->b_data);
- source = kmap_atomic(page);
+ source = kmap_local_folio(bh->b_folio, bh_offset(bh));
/* Fire data frozen trigger just before we copy the data */
- jbd2_buffer_frozen_trigger(jh, source + offset, jh->b_triggers);
- memcpy(jh->b_frozen_data, source + offset, bh->b_size);
- kunmap_atomic(source);
+ jbd2_buffer_frozen_trigger(jh, source, jh->b_triggers);
+ memcpy(jh->b_frozen_data, source, bh->b_size);
+ kunmap_local(source);
/*
* Now that the frozen data is saved off, we need to store any matching
@@ -970,7 +956,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
journal = transaction->t_journal;
- jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
+ jbd2_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
JBUFFER_TRACE(jh, "entry");
repeat:
@@ -1001,36 +987,28 @@ repeat:
* ie. locked but not dirty) or tune2fs (which may actually have
* the buffer dirtied, ugh.) */
- if (buffer_dirty(bh)) {
- /*
- * First question: is this buffer already part of the current
- * transaction or the existing committing transaction?
- */
- if (jh->b_transaction) {
- J_ASSERT_JH(jh,
- jh->b_transaction == transaction ||
- jh->b_transaction ==
- journal->j_committing_transaction);
- if (jh->b_next_transaction)
- J_ASSERT_JH(jh, jh->b_next_transaction ==
- transaction);
- warn_dirty_buffer(bh);
- }
+ if (buffer_dirty(bh) && jh->b_transaction) {
+ warn_dirty_buffer(bh);
/*
- * In any case we need to clean the dirty flag and we must
- * do it under the buffer lock to be sure we don't race
- * with running write-out.
+ * We need to clean the dirty flag and we must do it under the
+ * buffer lock to be sure we don't race with running write-out.
*/
JBUFFER_TRACE(jh, "Journalling dirty buffer");
clear_buffer_dirty(bh);
+ /*
+ * The buffer is going to be added to BJ_Reserved list now and
+ * nothing guarantees jbd2_journal_dirty_metadata() will be
+ * ever called for it. So we need to set jbddirty bit here to
+ * make sure the buffer is dirtied and written out when the
+ * journaling machinery is done with it.
+ */
set_buffer_jbddirty(bh);
}
- unlock_buffer(bh);
-
error = -EROFS;
if (is_handle_aborted(handle)) {
spin_unlock(&jh->b_state_lock);
+ unlock_buffer(bh);
goto out;
}
error = 0;
@@ -1040,8 +1018,10 @@ repeat:
* b_next_transaction points to it
*/
if (jh->b_transaction == transaction ||
- jh->b_next_transaction == transaction)
+ jh->b_next_transaction == transaction) {
+ unlock_buffer(bh);
goto done;
+ }
/*
* this is the first time this transaction is touching this buffer,
@@ -1065,10 +1045,24 @@ repeat:
*/
smp_wmb();
spin_lock(&journal->j_list_lock);
+ if (test_clear_buffer_dirty(bh)) {
+ /*
+ * Execute buffer dirty clearing and jh->b_transaction
+ * assignment under journal->j_list_lock locked to
+ * prevent bh being removed from checkpoint list if
+ * the buffer is in an intermediate state (not dirty
+ * and jh->b_transaction is NULL).
+ */
+ JBUFFER_TRACE(jh, "Journalling dirty buffer");
+ set_buffer_jbddirty(bh);
+ }
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
spin_unlock(&journal->j_list_lock);
+ unlock_buffer(bh);
goto done;
}
+ unlock_buffer(bh);
+
/*
* If there is already a copy-out version of this buffer, then we don't
* need to make another one
@@ -1218,11 +1212,26 @@ out:
int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
{
struct journal_head *jh;
+ journal_t *journal;
int rc;
if (is_handle_aborted(handle))
return -EROFS;
+ journal = handle->h_transaction->t_journal;
+ rc = jbd2_check_fs_dev_write_error(journal);
+ if (rc) {
+ /*
+ * If the fs dev has writeback errors, it may have failed
+ * to async write out metadata buffers in the background.
+ * In this case, we could read old data from disk and write
+ * it out again, which may lead to on-disk filesystem
+ * inconsistency. Aborting journal can avoid it happen.
+ */
+ jbd2_journal_abort(journal, rc);
+ return -EIO;
+ }
+
if (jbd2_write_access_granted(handle, bh, false))
return 0;
@@ -1262,7 +1271,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
struct journal_head *jh = jbd2_journal_add_journal_head(bh);
int err;
- jbd_debug(5, "journal_head %p\n", jh);
+ jbd2_debug(5, "journal_head %p\n", jh);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
@@ -1276,14 +1285,23 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
* committing transaction's lists, but it HAS to be in Forget state in
* that case: the transaction must have deleted the buffer for it to be
* reused here.
+ * In the case of file system data inconsistency, for example, if the
+ * block bitmap of a referenced block is not set, it can lead to the
+ * situation where a block being committed is allocated and used again.
+ * As a result, the following condition will not be satisfied, so here
+ * we directly trigger a JBD abort instead of immediately invoking
+ * bugon.
*/
spin_lock(&jh->b_state_lock);
- J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
- jh->b_transaction == NULL ||
- (jh->b_transaction == journal->j_committing_transaction &&
- jh->b_jlist == BJ_Forget)));
+ if (!(jh->b_transaction == transaction || jh->b_transaction == NULL ||
+ (jh->b_transaction == journal->j_committing_transaction &&
+ jh->b_jlist == BJ_Forget)) || jh->b_next_transaction != NULL) {
+ err = -EROFS;
+ spin_unlock(&jh->b_state_lock);
+ jbd2_journal_abort(journal, err);
+ goto out;
+ }
- J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
if (jh->b_transaction == NULL) {
@@ -1477,8 +1495,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
struct journal_head *jh;
int ret = 0;
- if (is_handle_aborted(handle))
- return -EROFS;
if (!buffer_jbd(bh))
return -EUCLEAN;
@@ -1487,7 +1503,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
* of the running transaction.
*/
jh = bh2jh(bh);
- jbd_debug(5, "journal_head %p\n", jh);
+ jbd2_debug(5, "journal_head %p\n", jh);
JBUFFER_TRACE(jh, "entry");
/*
@@ -1503,7 +1519,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
jh->b_next_transaction == transaction);
spin_unlock(&jh->b_state_lock);
}
- if (jh->b_modified == 1) {
+ if (data_race(jh->b_modified == 1)) {
/* If it's in our transaction it must be in BJ_Metadata list. */
if (data_race(jh->b_transaction == transaction &&
jh->b_jlist != BJ_Metadata)) {
@@ -1522,9 +1538,22 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
goto out;
}
- journal = transaction->t_journal;
spin_lock(&jh->b_state_lock);
+ if (is_handle_aborted(handle)) {
+ /*
+ * Check journal aborting with @jh->b_state_lock locked,
+ * since 'jh->b_transaction' could be replaced with
+ * 'jh->b_next_transaction' during old transaction
+ * committing if journal aborted, which may fail
+ * assertion on 'jh->b_frozen_data == NULL'.
+ */
+ ret = -EROFS;
+ goto out_unlock_bh;
+ }
+
+ journal = transaction->t_journal;
+
if (jh->b_modified == 0) {
/*
* This buffer's got modified and becoming part
@@ -1640,6 +1669,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
int drop_reserve = 0;
int err = 0;
int was_modified = 0;
+ int wait_for_writeback = 0;
if (is_handle_aborted(handle))
return -EROFS;
@@ -1757,25 +1787,28 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
* 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);
+ if (jbd2_journal_try_remove_checkpoint(jh) >= 0) {
spin_unlock(&journal->j_list_lock);
goto drop;
}
/*
- * 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.
+ * The buffer has not yet been written to disk. We should
+ * either clear the buffer or ensure that the ongoing I/O
+ * is completed, and attach this buffer to current
+ * transaction so that the buffer can be checkpointed only
+ * after the current transaction commits.
*/
clear_buffer_dirty(bh);
+ wait_for_writeback = 1;
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
spin_unlock(&journal->j_list_lock);
}
drop:
__brelse(bh);
spin_unlock(&jh->b_state_lock);
+ if (wait_for_writeback)
+ wait_on_buffer(bh);
jbd2_journal_put_journal_head(jh);
if (drop_reserve) {
/* no need to reserve log space for this block -bzzz */
@@ -1809,7 +1842,7 @@ int jbd2_journal_stop(handle_t *handle)
pid_t pid;
if (--handle->h_ref > 0) {
- jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
+ jbd2_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
handle->h_ref);
if (is_handle_aborted(handle))
return -EIO;
@@ -1829,7 +1862,7 @@ int jbd2_journal_stop(handle_t *handle)
if (is_handle_aborted(handle))
err = -EIO;
- jbd_debug(4, "Handle %p going down\n", handle);
+ jbd2_debug(4, "Handle %p going down\n", handle);
trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev,
tid, handle->h_type, handle->h_line_no,
jiffies - handle->h_start_jiffies,
@@ -1907,7 +1940,7 @@ int jbd2_journal_stop(handle_t *handle)
* completes the commit thread, it just doesn't write
* anything to disk. */
- jbd_debug(2, "transaction too old, requesting commit for "
+ jbd2_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
/* This is non-blocking */
jbd2_log_start_commit(journal, tid);
@@ -2058,54 +2091,10 @@ static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
jh->b_transaction = NULL;
}
-void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
-{
- struct buffer_head *bh = jh2bh(jh);
-
- /* Get reference so that buffer cannot be freed before we unlock it */
- get_bh(bh);
- spin_lock(&jh->b_state_lock);
- spin_lock(&journal->j_list_lock);
- __jbd2_journal_unfile_buffer(jh);
- spin_unlock(&journal->j_list_lock);
- spin_unlock(&jh->b_state_lock);
- jbd2_journal_put_journal_head(jh);
- __brelse(bh);
-}
-
-/*
- * Called from jbd2_journal_try_to_free_buffers().
- *
- * Called under jh->b_state_lock
- */
-static void
-__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
-{
- struct journal_head *jh;
-
- jh = bh2jh(bh);
-
- if (buffer_locked(bh) || buffer_dirty(bh))
- goto out;
-
- if (jh->b_next_transaction != NULL || jh->b_transaction != NULL)
- goto out;
-
- spin_lock(&journal->j_list_lock);
- if (jh->b_cp_transaction != NULL) {
- /* written-back checkpointed metadata buffer */
- JBUFFER_TRACE(jh, "remove from checkpoint list");
- __jbd2_journal_remove_checkpoint(jh);
- }
- spin_unlock(&journal->j_list_lock);
-out:
- return;
-}
-
/**
* jbd2_journal_try_to_free_buffers() - try to free page buffers.
* @journal: journal for operation
- * @page: to try and free
+ * @folio: Folio to detach data from.
*
* For all the buffers on this page,
* if they are fully written out ordered data, move them onto BUF_CLEAN
@@ -2134,17 +2123,17 @@ out:
* cannot happen because we never reallocate freed data as metadata
* while the data is part of a transaction. Yes?
*
- * Return 0 on failure, 1 on success
+ * Return false on failure, true on success
*/
-int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
+bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio)
{
struct buffer_head *head;
struct buffer_head *bh;
- int ret = 0;
+ bool ret = false;
- J_ASSERT(PageLocked(page));
+ J_ASSERT(folio_test_locked(folio));
- head = page_buffers(page);
+ head = folio_buffers(folio);
bh = head;
do {
struct journal_head *jh;
@@ -2159,14 +2148,20 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
continue;
spin_lock(&jh->b_state_lock);
- __journal_try_to_free_buffer(journal, bh);
+ if (!jh->b_transaction && !jh->b_next_transaction) {
+ spin_lock(&journal->j_list_lock);
+ /* Remove written-back checkpointed metadata buffer */
+ if (jh->b_cp_transaction != NULL)
+ jbd2_journal_try_remove_checkpoint(jh);
+ spin_unlock(&journal->j_list_lock);
+ }
spin_unlock(&jh->b_state_lock);
jbd2_journal_put_journal_head(jh);
if (buffer_jbd(bh))
goto busy;
} while ((bh = bh->b_this_page) != head);
- ret = try_to_free_buffers(page);
+ ret = try_to_free_buffers(folio);
busy:
return ret;
}
@@ -2194,7 +2189,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
/*
* We don't want to write the buffer anymore, clear the
* bit so that we don't confuse checks in
- * __journal_file_buffer
+ * __jbd2_journal_file_buffer
*/
clear_buffer_dirty(bh);
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
@@ -2208,14 +2203,14 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
}
/*
- * jbd2_journal_invalidatepage
+ * jbd2_journal_invalidate_folio
*
* This code is tricky. It has a number of cases to deal with.
*
* There are two invariants which this code relies on:
*
- * i_size must be updated on disk before we start calling invalidatepage on the
- * data.
+ * i_size must be updated on disk before we start calling invalidate_folio
+ * on the data.
*
* This is done in ext3 by defining an ext3_setattr method which
* updates i_size before truncate gets going. By maintaining this
@@ -2360,6 +2355,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
spin_unlock(&jh->b_state_lock);
write_unlock(&journal->j_state_lock);
jbd2_journal_put_journal_head(jh);
+ /* Already zapped buffer? Nothing to do... */
+ if (!bh->b_bdev)
+ return 0;
return -EBUSY;
}
/*
@@ -2417,9 +2415,9 @@ zap_buffer_unlocked:
}
/**
- * jbd2_journal_invalidatepage()
+ * jbd2_journal_invalidate_folio()
* @journal: journal to use for flush...
- * @page: page to flush
+ * @folio: folio to flush
* @offset: start of the range to invalidate
* @length: length of the range to invalidate
*
@@ -2428,30 +2426,29 @@ zap_buffer_unlocked:
* the page is straddling i_size. Caller then has to wait for current commit
* and try again.
*/
-int jbd2_journal_invalidatepage(journal_t *journal,
- struct page *page,
- unsigned int offset,
- unsigned int length)
+int jbd2_journal_invalidate_folio(journal_t *journal, struct folio *folio,
+ size_t offset, size_t length)
{
struct buffer_head *head, *bh, *next;
unsigned int stop = offset + length;
unsigned int curr_off = 0;
- int partial_page = (offset || length < PAGE_SIZE);
+ int partial_page = (offset || length < folio_size(folio));
int may_free = 1;
int ret = 0;
- if (!PageLocked(page))
+ if (!folio_test_locked(folio))
BUG();
- if (!page_has_buffers(page))
+ head = folio_buffers(folio);
+ if (!head)
return 0;
- BUG_ON(stop > PAGE_SIZE || stop < length);
+ BUG_ON(stop > folio_size(folio) || stop < length);
/* We will potentially be playing with lists other than just the
* data lists (especially for journaled data mode), so be
* cautious in our locking. */
- head = bh = page_buffers(page);
+ bh = head;
do {
unsigned int next_off = curr_off + bh->b_size;
next = bh->b_this_page;
@@ -2474,8 +2471,8 @@ int jbd2_journal_invalidatepage(journal_t *journal,
} while (bh != head);
if (!partial_page) {
- if (may_free && try_to_free_buffers(page))
- J_ASSERT(!page_has_buffers(page));
+ if (may_free && try_to_free_buffers(folio))
+ J_ASSERT(!folio_buffers(folio));
}
return 0;
}
@@ -2654,7 +2651,7 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
return -EROFS;
journal = transaction->t_journal;
- jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino,
+ jbd2_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino,
transaction->t_tid);
spin_lock(&journal->j_list_lock);
generated by cgit (git 2.34.1) at 2025-12-26 05:16:38 +0000