aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/fs/nilfs2/segment.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--fs/nilfs2/segment.c68
1 files changed, 54 insertions, 14 deletions
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 8654ab8ad534..6ea81f1d5094 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1652,6 +1652,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
if (bh->b_folio != bd_folio) {
if (bd_folio) {
folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
folio_clear_dirty_for_io(bd_folio);
folio_start_writeback(bd_folio);
folio_unlock(bd_folio);
@@ -1665,6 +1666,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
if (bh == segbuf->sb_super_root) {
if (bh->b_folio != bd_folio) {
folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
folio_clear_dirty_for_io(bd_folio);
folio_start_writeback(bd_folio);
folio_unlock(bd_folio);
@@ -1681,6 +1683,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
}
if (bd_folio) {
folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
folio_clear_dirty_for_io(bd_folio);
folio_start_writeback(bd_folio);
folio_unlock(bd_folio);
@@ -2118,8 +2121,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci)
{
spin_lock(&sci->sc_state_lock);
if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) {
- sci->sc_timer.expires = jiffies + sci->sc_interval;
- add_timer(&sci->sc_timer);
+ if (sci->sc_task) {
+ sci->sc_timer.expires = jiffies + sci->sc_interval;
+ add_timer(&sci->sc_timer);
+ }
sci->sc_state |= NILFS_SEGCTOR_COMMIT;
}
spin_unlock(&sci->sc_state_lock);
@@ -2166,19 +2171,36 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci)
struct nilfs_segctor_wait_request wait_req;
int err = 0;
- spin_lock(&sci->sc_state_lock);
init_wait(&wait_req.wq);
wait_req.err = 0;
atomic_set(&wait_req.done, 0);
+ init_waitqueue_entry(&wait_req.wq, current);
+
+ /*
+ * To prevent a race issue where completion notifications from the
+ * log writer thread are missed, increment the request sequence count
+ * "sc_seq_request" and insert a wait queue entry using the current
+ * sequence number into the "sc_wait_request" queue at the same time
+ * within the lock section of "sc_state_lock".
+ */
+ spin_lock(&sci->sc_state_lock);
wait_req.seq = ++sci->sc_seq_request;
+ add_wait_queue(&sci->sc_wait_request, &wait_req.wq);
spin_unlock(&sci->sc_state_lock);
- init_waitqueue_entry(&wait_req.wq, current);
- add_wait_queue(&sci->sc_wait_request, &wait_req.wq);
- set_current_state(TASK_INTERRUPTIBLE);
wake_up(&sci->sc_wait_daemon);
for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /*
+ * Synchronize only while the log writer thread is alive.
+ * Leave flushing out after the log writer thread exits to
+ * the cleanup work in nilfs_segctor_destroy().
+ */
+ if (!sci->sc_task)
+ break;
+
if (atomic_read(&wait_req.done)) {
err = wait_req.err;
break;
@@ -2194,7 +2216,7 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci)
return err;
}
-static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
+static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force)
{
struct nilfs_segctor_wait_request *wrq, *n;
unsigned long flags;
@@ -2202,7 +2224,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
spin_lock_irqsave(&sci->sc_wait_request.lock, flags);
list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) {
if (!atomic_read(&wrq->done) &&
- nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) {
+ (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) {
wrq->err = err;
atomic_set(&wrq->done, 1);
}
@@ -2320,10 +2342,21 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
*/
static void nilfs_segctor_accept(struct nilfs_sc_info *sci)
{
+ bool thread_is_alive;
+
spin_lock(&sci->sc_state_lock);
sci->sc_seq_accepted = sci->sc_seq_request;
+ thread_is_alive = (bool)sci->sc_task;
spin_unlock(&sci->sc_state_lock);
- del_timer_sync(&sci->sc_timer);
+
+ /*
+ * This function does not race with the log writer thread's
+ * termination. Therefore, deleting sc_timer, which should not be
+ * done after the log writer thread exits, can be done safely outside
+ * the area protected by sc_state_lock.
+ */
+ if (thread_is_alive)
+ del_timer_sync(&sci->sc_timer);
}
/**
@@ -2340,7 +2373,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
if (mode == SC_LSEG_SR) {
sci->sc_state &= ~NILFS_SEGCTOR_COMMIT;
sci->sc_seq_done = sci->sc_seq_accepted;
- nilfs_segctor_wakeup(sci, err);
+ nilfs_segctor_wakeup(sci, err, false);
sci->sc_flush_request = 0;
} else {
if (mode == SC_FLUSH_FILE)
@@ -2349,7 +2382,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
sci->sc_flush_request &= ~FLUSH_DAT_BIT;
/* re-enable timer if checkpoint creation was not done */
- if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) &&
+ if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task &&
time_before(jiffies, sci->sc_timer.expires))
add_timer(&sci->sc_timer);
}
@@ -2539,6 +2572,7 @@ static int nilfs_segctor_thread(void *arg)
int timeout = 0;
sci->sc_timer_task = current;
+ timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
/* start sync. */
sci->sc_task = current;
@@ -2606,6 +2640,7 @@ static int nilfs_segctor_thread(void *arg)
end_thread:
/* end sync. */
sci->sc_task = NULL;
+ timer_shutdown_sync(&sci->sc_timer);
wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */
spin_unlock(&sci->sc_state_lock);
return 0;
@@ -2669,7 +2704,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
INIT_LIST_HEAD(&sci->sc_gc_inodes);
INIT_LIST_HEAD(&sci->sc_iput_queue);
INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
- timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ;
@@ -2723,6 +2757,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
|| sci->sc_seq_request != sci->sc_seq_done);
spin_unlock(&sci->sc_state_lock);
+ /*
+ * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can
+ * be called from delayed iput() via nilfs_evict_inode() and can race
+ * with the above log writer thread termination.
+ */
+ nilfs_segctor_wakeup(sci, 0, true);
+
if (flush_work(&sci->sc_iput_work))
flag = true;
@@ -2748,7 +2789,6 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
down_write(&nilfs->ns_segctor_sem);
- timer_shutdown_sync(&sci->sc_timer);
kfree(sci);
}
@@ -2784,7 +2824,7 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
if (!nilfs->ns_writer)
return -ENOMEM;
- inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL);
+ inode_attach_wb(nilfs->ns_bdev->bd_mapping->host, NULL);
err = nilfs_segctor_start_thread(nilfs->ns_writer);
if (unlikely(err))
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.