1 files changed, 127 insertions, 64 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3d84fcc471c6..3cd99e2dc6ac 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -141,8 +141,32 @@ static void wb_wakeup(struct bdi_writeback *wb)
 	spin_unlock_irq(&wb->work_lock);
 }
 
-static void finish_writeback_work(struct bdi_writeback *wb,
-				  struct wb_writeback_work *work)
+/*
+ * This function is used when the first inode for this wb is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
+ */
+static void wb_wakeup_delayed(struct bdi_writeback *wb)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	spin_lock_irq(&wb->work_lock);
+	if (test_bit(WB_registered, &wb->state))
+		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
+	spin_unlock_irq(&wb->work_lock);
+}
+
+static void finish_writeback_work(struct wb_writeback_work *work)
 {
 	struct wb_completion *done = work->done;
 
@@ -171,7 +195,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 		list_add_tail(&work->list, &wb->work_list);
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	} else
-		finish_writeback_work(wb, work);
+		finish_writeback_work(work);
 
 	spin_unlock_irq(&wb->work_lock);
 }
@@ -266,7 +290,6 @@ void __inode_attach_wb(struct inode *inode, struct folio *folio)
 	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
 		wb_put(wb);
 }
-EXPORT_SYMBOL_GPL(__inode_attach_wb);
 
 /**
  * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list
@@ -707,8 +730,9 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb)
  * writeback completion, wbc_detach_inode() should be called.  This is used
  * to track the cgroup writeback context.
  */
-void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
-				 struct inode *inode)
+static void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+		struct inode *inode)
+	__releases(&inode->i_lock)
 {
 	if (!inode_cgwb_enabled(inode)) {
 		spin_unlock(&inode->i_lock);
@@ -738,7 +762,24 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 	if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
 		inode_switch_wbs(inode, wbc->wb_id);
 }
-EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
+
+/**
+ * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite
+ * @wbc: writeback_control of interest
+ * @inode: target inode
+ *
+ * This function is to be used by __filemap_fdatawrite_range(), which is an
+ * alternative entry point into writeback code, and first ensures @inode is
+ * associated with a bdi_writeback and attaches it to @wbc.
+ */
+void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
+		struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	inode_attach_wb(inode, NULL);
+	wbc_attach_and_unlock_inode(wbc, inode);
+}
+EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode);
 
 /**
  * wbc_detach_inode - disassociate wbc from inode and perform foreign detection
@@ -866,17 +907,16 @@ EXPORT_SYMBOL_GPL(wbc_detach_inode);
 /**
  * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership
  * @wbc: writeback_control of the writeback in progress
- * @page: page being written out
+ * @folio: folio being written out
  * @bytes: number of bytes being written out
  *
- * @bytes from @page are about to written out during the writeback
+ * @bytes from @folio are about to written out during the writeback
  * controlled by @wbc.  Keep the book for foreign inode detection.  See
  * wbc_detach_inode().
  */
-void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
 			      size_t bytes)
 {
-	struct folio *folio;
 	struct cgroup_subsys_state *css;
 	int id;
 
@@ -889,7 +929,6 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
 	if (!wbc->wb || wbc->no_cgroup_owner)
 		return;
 
-	folio = page_folio(page);
 	css = mem_cgroup_css_from_folio(folio);
 	/* dead cgroups shouldn't contribute to inode ownership arbitration */
 	if (!(css->flags & CSS_ONLINE))
@@ -1108,6 +1147,7 @@ out_bdi_put:
 
 /**
  * cgroup_writeback_umount - flush inode wb switches for umount
+ * @sb: target super_block
  *
  * This function is called when a super_block is about to be destroyed and
  * flushes in-flight inode wb switches.  An inode wb switch goes through
@@ -1116,8 +1156,12 @@ out_bdi_put:
  * rare occurrences and synchronize_rcu() can take a while, perform
  * flushing iff wb switches are in flight.
  */
-void cgroup_writeback_umount(void)
+void cgroup_writeback_umount(struct super_block *sb)
 {
+
+	if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK))
+		return;
+
 	/*
 	 * SB_ACTIVE should be reliably cleared before checking
 	 * isw_nr_in_flight, see generic_shutdown_super().
@@ -1198,6 +1242,13 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 	}
 }
 
+static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+					       struct inode *inode)
+	__releases(&inode->i_lock)
+{
+	spin_unlock(&inode->i_lock);
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 /*
@@ -1357,12 +1408,13 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 
 static void inode_sync_complete(struct inode *inode)
 {
+	assert_spin_locked(&inode->i_lock);
+
 	inode->i_state &= ~I_SYNC;
 	/* If inode is clean an unused, put it into LRU now... */
 	inode_add_lru(inode);
-	/* Waiters must see I_SYNC cleared before being woken up */
-	smp_mb();
-	wake_up_bit(&inode->i_state, __I_SYNC);
+	/* Called with inode->i_lock which ensures memory ordering. */
+	inode_wake_up_bit(inode, __I_SYNC);
 }
 
 static bool inode_dirtied_after(struct inode *inode, unsigned long t)
@@ -1481,30 +1533,27 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc)
  * Wait for writeback on an inode to complete. Called with i_lock held.
  * Caller must make sure inode cannot go away when we drop i_lock.
  */
-static void __inode_wait_for_writeback(struct inode *inode)
-	__releases(inode->i_lock)
-	__acquires(inode->i_lock)
+void inode_wait_for_writeback(struct inode *inode)
 {
-	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
-	wait_queue_head_t *wqh;
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
+
+	assert_spin_locked(&inode->i_lock);
+
+	if (!(inode->i_state & I_SYNC))
+		return;
 
-	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	while (inode->i_state & I_SYNC) {
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
+	for (;;) {
+		prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
+		/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
+		if (!(inode->i_state & I_SYNC))
+			break;
 		spin_unlock(&inode->i_lock);
-		__wait_on_bit(wqh, &wq, bit_wait,
-			      TASK_UNINTERRUPTIBLE);
+		schedule();
 		spin_lock(&inode->i_lock);
 	}
-}
-
-/*
- * Wait for writeback on an inode to complete. Caller must have inode pinned.
- */
-void inode_wait_for_writeback(struct inode *inode)
-{
-	spin_lock(&inode->i_lock);
-	__inode_wait_for_writeback(inode);
-	spin_unlock(&inode->i_lock);
+	finish_wait(wq_head, &wqe.wq_entry);
 }
 
 /*
@@ -1515,16 +1564,20 @@ void inode_wait_for_writeback(struct inode *inode)
 static void inode_sleep_on_writeback(struct inode *inode)
 	__releases(inode->i_lock)
 {
-	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	int sleep;
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
+	bool sleep;
 
-	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
-	sleep = inode->i_state & I_SYNC;
+	assert_spin_locked(&inode->i_lock);
+
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
+	prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
+	/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
+	sleep = !!(inode->i_state & I_SYNC);
 	spin_unlock(&inode->i_lock);
 	if (sleep)
 		schedule();
-	finish_wait(wqh, &wait);
+	finish_wait(wq_head, &wqe.wq_entry);
 }
 
 /*
@@ -1536,7 +1589,8 @@ static void inode_sleep_on_writeback(struct inode *inode)
  * thread's back can have unexpected consequences.
  */
 static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
-			  struct writeback_control *wbc)
+			  struct writeback_control *wbc,
+			  unsigned long dirtied_before)
 {
 	if (inode->i_state & I_FREEING)
 		return;
@@ -1569,7 +1623,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * We didn't write back all the pages.  nfs_writepages()
 		 * sometimes bales out without doing anything.
 		 */
-		if (wbc->nr_to_write <= 0) {
+		if (wbc->nr_to_write <= 0 &&
+		    !inode_dirtied_after(inode, dirtied_before)) {
 			/* Slice used up. Queue for next turn. */
 			requeue_io(inode, wb);
 		} else {
@@ -1726,7 +1781,7 @@ static int writeback_single_inode(struct inode *inode,
 		 */
 		if (wbc->sync_mode != WB_SYNC_ALL)
 			goto out;
-		__inode_wait_for_writeback(inode);
+		inode_wait_for_writeback(inode);
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
@@ -1837,6 +1892,11 @@ static long writeback_sb_inodes(struct super_block *sb,
 	unsigned long start_time = jiffies;
 	long write_chunk;
 	long total_wrote = 0;  /* count both pages and inodes */
+	unsigned long dirtied_before = jiffies;
+
+	if (work->for_kupdate)
+		dirtied_before = jiffies -
+			msecs_to_jiffies(dirty_expire_interval * 10);
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
@@ -1942,7 +2002,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			total_wrote++;
-		requeue_inode(inode, tmp_wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc, dirtied_before);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
@@ -2044,6 +2104,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 	struct inode *inode;
 	long progress;
 	struct blk_plug plug;
+	bool queued = false;
 
 	blk_start_plug(&plug);
 	for (;;) {
@@ -2073,21 +2134,24 @@ static long wb_writeback(struct bdi_writeback *wb,
 
 		spin_lock(&wb->list_lock);
 
-		/*
-		 * Kupdate and background works are special and we want to
-		 * include all inodes that need writing. Livelock avoidance is
-		 * handled by these works yielding to any other work so we are
-		 * safe.
-		 */
-		if (work->for_kupdate) {
-			dirtied_before = jiffies -
-				msecs_to_jiffies(dirty_expire_interval * 10);
-		} else if (work->for_background)
-			dirtied_before = jiffies;
-
 		trace_writeback_start(wb, work);
-		if (list_empty(&wb->b_io))
+		if (list_empty(&wb->b_io)) {
+			/*
+			 * Kupdate and background works are special and we want
+			 * to include all inodes that need writing. Livelock
+			 * avoidance is handled by these works yielding to any
+			 * other work so we are safe.
+			 */
+			if (work->for_kupdate) {
+				dirtied_before = jiffies -
+					msecs_to_jiffies(dirty_expire_interval *
+							 10);
+			} else if (work->for_background)
+				dirtied_before = jiffies;
+
 			queue_io(wb, work, dirtied_before);
+			queued = true;
+		}
 		if (work->sb)
 			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
@@ -2102,7 +2166,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * mean the overall work is done. So we keep looping as long
 		 * as made some progress on cleaning pages or inodes.
 		 */
-		if (progress) {
+		if (progress || !queued) {
 			spin_unlock(&wb->list_lock);
 			continue;
 		}
@@ -2237,7 +2301,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	while ((work = get_next_work_item(wb)) != NULL) {
 		trace_writeback_exec(wb, work);
 		wrote += wb_writeback(wb, work);
-		finish_writeback_work(wb, work);
+		finish_writeback_work(work);
 	}
 
 	/*
@@ -2297,8 +2361,7 @@ void wb_workfn(struct work_struct *work)
 }
 
 /*
- * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero,
- * write back the whole world.
+ * Start writeback of all dirty pages on this bdi.
  */
 static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
 					 enum wb_reason reason)
@@ -2379,7 +2442,7 @@ static int __init start_dirtytime_writeback(void)
 }
 __initcall(start_dirtytime_writeback);
 
-int dirtytime_interval_handler(struct ctl_table *table, int write,
+int dirtytime_interval_handler(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2701,7 +2764,7 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr);
  */
 void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 {
-	return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
+	writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
 }
 EXPORT_SYMBOL(writeback_inodes_sb);