1 files changed, 206 insertions, 131 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 539f36cf3e4a..41a3ccff18d8 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -231,11 +231,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 
 static void inode_sync_complete(struct inode *inode)
 {
-	/*
-	 * Prevent speculative execution through
-	 * spin_unlock(&wb->list_lock);
-	 */
-
+	inode->i_state &= ~I_SYNC;
+	/* Waiters must see I_SYNC cleared before being woken up */
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_SYNC);
 }
@@ -329,10 +326,12 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc)
 }
 
 /*
- * Wait for writeback on an inode to complete.
+ * 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,
-				     struct bdi_writeback *wb)
+static void __inode_wait_for_writeback(struct inode *inode)
+	__releases(inode->i_lock)
+	__acquires(inode->i_lock)
 {
 	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
 	wait_queue_head_t *wqh;
@@ -340,70 +339,119 @@ static void inode_wait_for_writeback(struct inode *inode,
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	while (inode->i_state & I_SYNC) {
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&wb->list_lock);
 		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
-		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
 	}
 }
 
 /*
- * Write out an inode's dirty pages.  Called under wb->list_lock and
- * inode->i_lock.  Either the caller has an active reference on the inode or
- * the inode has I_WILL_FREE set.
- *
- * If `wait' is set, wait on the writeout.
- *
- * The whole writeout design is quite complex and fragile.  We want to avoid
- * starvation of particular inodes when others are being redirtied, prevent
- * livelocks, etc.
+ * Wait for writeback on an inode to complete. Caller must have inode pinned.
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+void inode_wait_for_writeback(struct inode *inode)
 {
-	struct address_space *mapping = inode->i_mapping;
-	long nr_to_write = wbc->nr_to_write;
-	unsigned dirty;
-	int ret;
+	spin_lock(&inode->i_lock);
+	__inode_wait_for_writeback(inode);
+	spin_unlock(&inode->i_lock);
+}
 
-	assert_spin_locked(&wb->list_lock);
-	assert_spin_locked(&inode->i_lock);
+/*
+ * Sleep until I_SYNC is cleared. This function must be called with i_lock
+ * held and drops it. It is aimed for callers not holding any inode reference
+ * so once i_lock is dropped, inode can go away.
+ */
+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;
 
-	if (!atomic_read(&inode->i_count))
-		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
-	else
-		WARN_ON(inode->i_state & I_WILL_FREE);
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	sleep = inode->i_state & I_SYNC;
+	spin_unlock(&inode->i_lock);
+	if (sleep)
+		schedule();
+	finish_wait(wqh, &wait);
+}
 
-	if (inode->i_state & I_SYNC) {
+/*
+ * Find proper writeback list for the inode depending on its current state and
+ * possibly also change of its state while we were doing writeback.  Here we
+ * handle things such as livelock prevention or fairness of writeback among
+ * inodes. This function can be called only by flusher thread - noone else
+ * processes all inodes in writeback lists and requeueing inodes behind flusher
+ * thread's back can have unexpected consequences.
+ */
+static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
+			  struct writeback_control *wbc)
+{
+	if (inode->i_state & I_FREEING)
+		return;
+
+	/*
+	 * Sync livelock prevention. Each inode is tagged and synced in one
+	 * shot. If still dirty, it will be redirty_tail()'ed below.  Update
+	 * the dirty time to prevent enqueue and sync it again.
+	 */
+	if ((inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
+		inode->dirtied_when = jiffies;
+
+	if (wbc->pages_skipped) {
 		/*
-		 * If this inode is locked for writeback and we are not doing
-		 * writeback-for-data-integrity, move it to b_more_io so that
-		 * writeback can proceed with the other inodes on s_io.
-		 *
-		 * We'll have another go at writing back this inode when we
-		 * completed a full scan of b_io.
+		 * writeback is not making progress due to locked
+		 * buffers. Skip this inode for now.
 		 */
-		if (wbc->sync_mode != WB_SYNC_ALL) {
+		redirty_tail(inode, wb);
+		return;
+	}
+
+	if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
+		/*
+		 * We didn't write back all the pages.  nfs_writepages()
+		 * sometimes bales out without doing anything.
+		 */
+		if (wbc->nr_to_write <= 0) {
+			/* Slice used up. Queue for next turn. */
 			requeue_io(inode, wb);
-			trace_writeback_single_inode_requeue(inode, wbc,
-							     nr_to_write);
-			return 0;
+		} else {
+			/*
+			 * Writeback blocked by something other than
+			 * congestion. Delay the inode for some time to
+			 * avoid spinning on the CPU (100% iowait)
+			 * retrying writeback of the dirty page/inode
+			 * that cannot be performed immediately.
+			 */
+			redirty_tail(inode, wb);
 		}
-
+	} else if (inode->i_state & I_DIRTY) {
 		/*
-		 * It's a data-integrity sync.  We must wait.
+		 * Filesystems can dirty the inode during writeback operations,
+		 * such as delayed allocation during submission or metadata
+		 * updates after data IO completion.
 		 */
-		inode_wait_for_writeback(inode, wb);
+		redirty_tail(inode, wb);
+	} else {
+		/* The inode is clean. Remove from writeback lists. */
+		list_del_init(&inode->i_wb_list);
 	}
+}
 
-	BUG_ON(inode->i_state & I_SYNC);
+/*
+ * Write out an inode and its dirty pages. Do not update the writeback list
+ * linkage. That is left to the caller. The caller is also responsible for
+ * setting I_SYNC flag and calling inode_sync_complete() to clear it.
+ */
+static int
+__writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
+			 struct writeback_control *wbc)
+{
+	struct address_space *mapping = inode->i_mapping;
+	long nr_to_write = wbc->nr_to_write;
+	unsigned dirty;
+	int ret;
 
-	/* Set I_SYNC, reset I_DIRTY_PAGES */
-	inode->i_state |= I_SYNC;
-	inode->i_state &= ~I_DIRTY_PAGES;
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
+	WARN_ON(!(inode->i_state & I_SYNC));
 
 	ret = do_writepages(mapping, wbc);
 
@@ -424,6 +472,9 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
+	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
+	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		inode->i_state &= ~I_DIRTY_PAGES;
 	dirty = inode->i_state & I_DIRTY;
 	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 	spin_unlock(&inode->i_lock);
@@ -433,60 +484,67 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 		if (ret == 0)
 			ret = err;
 	}
+	trace_writeback_single_inode(inode, wbc, nr_to_write);
+	return ret;
+}
+
+/*
+ * Write out an inode's dirty pages. Either the caller has an active reference
+ * on the inode or the inode has I_WILL_FREE set.
+ *
+ * This function is designed to be called for writing back one inode which
+ * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
+ * and does more profound writeback list handling in writeback_sb_inodes().
+ */
+static int
+writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
+		       struct writeback_control *wbc)
+{
+	int ret = 0;
 
-	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
-	inode->i_state &= ~I_SYNC;
-	if (!(inode->i_state & I_FREEING)) {
+	if (!atomic_read(&inode->i_count))
+		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
+	else
+		WARN_ON(inode->i_state & I_WILL_FREE);
+
+	if (inode->i_state & I_SYNC) {
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			goto out;
 		/*
-		 * Sync livelock prevention. Each inode is tagged and synced in
-		 * one shot. If still dirty, it will be redirty_tail()'ed below.
-		 * Update the dirty time to prevent enqueue and sync it again.
+		 * It's a data-integrity sync. We must wait. Since callers hold
+		 * inode reference or inode has I_WILL_FREE set, it cannot go
+		 * away under us.
 		 */
-		if ((inode->i_state & I_DIRTY) &&
-		    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
-			inode->dirtied_when = jiffies;
-
-		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-			/*
-			 * We didn't write back all the pages.  nfs_writepages()
-			 * sometimes bales out without doing anything.
-			 */
-			inode->i_state |= I_DIRTY_PAGES;
-			if (wbc->nr_to_write <= 0) {
-				/*
-				 * slice used up: queue for next turn
-				 */
-				requeue_io(inode, wb);
-			} else {
-				/*
-				 * Writeback blocked by something other than
-				 * congestion. Delay the inode for some time to
-				 * avoid spinning on the CPU (100% iowait)
-				 * retrying writeback of the dirty page/inode
-				 * that cannot be performed immediately.
-				 */
-				redirty_tail(inode, wb);
-			}
-		} else if (inode->i_state & I_DIRTY) {
-			/*
-			 * Filesystems can dirty the inode during writeback
-			 * operations, such as delayed allocation during
-			 * submission or metadata updates after data IO
-			 * completion.
-			 */
-			redirty_tail(inode, wb);
-		} else {
-			/*
-			 * The inode is clean.  At this point we either have
-			 * a reference to the inode or it's on it's way out.
-			 * No need to add it back to the LRU.
-			 */
-			list_del_init(&inode->i_wb_list);
-		}
+		__inode_wait_for_writeback(inode);
 	}
+	WARN_ON(inode->i_state & I_SYNC);
+	/*
+	 * Skip inode if it is clean. We don't want to mess with writeback
+	 * lists in this function since flusher thread may be doing for example
+	 * sync in parallel and if we move the inode, it could get skipped. So
+	 * here we make sure inode is on some writeback list and leave it there
+	 * unless we have completely cleaned the inode.
+	 */
+	if (!(inode->i_state & I_DIRTY))
+		goto out;
+	inode->i_state |= I_SYNC;
+	spin_unlock(&inode->i_lock);
+
+	ret = __writeback_single_inode(inode, wb, wbc);
+
+	spin_lock(&wb->list_lock);
+	spin_lock(&inode->i_lock);
+	/*
+	 * If inode is clean, remove it from writeback lists. Otherwise don't
+	 * touch it. See comment above for explanation.
+	 */
+	if (!(inode->i_state & I_DIRTY))
+		list_del_init(&inode->i_wb_list);
+	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
-	trace_writeback_single_inode(inode, wbc, nr_to_write);
+out:
+	spin_unlock(&inode->i_lock);
 	return ret;
 }
 
@@ -580,29 +638,58 @@ static long writeback_sb_inodes(struct super_block *sb,
 			redirty_tail(inode, wb);
 			continue;
 		}
-		__iget(inode);
+		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
+			/*
+			 * If this inode is locked for writeback and we are not
+			 * doing writeback-for-data-integrity, move it to
+			 * b_more_io so that writeback can proceed with the
+			 * other inodes on s_io.
+			 *
+			 * We'll have another go at writing back this inode
+			 * when we completed a full scan of b_io.
+			 */
+			spin_unlock(&inode->i_lock);
+			requeue_io(inode, wb);
+			trace_writeback_sb_inodes_requeue(inode);
+			continue;
+		}
+		spin_unlock(&wb->list_lock);
+
+		/*
+		 * We already requeued the inode if it had I_SYNC set and we
+		 * are doing WB_SYNC_NONE writeback. So this catches only the
+		 * WB_SYNC_ALL case.
+		 */
+		if (inode->i_state & I_SYNC) {
+			/* Wait for I_SYNC. This function drops i_lock... */
+			inode_sleep_on_writeback(inode);
+			/* Inode may be gone, start again */
+			spin_lock(&wb->list_lock);
+			continue;
+		}
+		inode->i_state |= I_SYNC;
+		spin_unlock(&inode->i_lock);
+
 		write_chunk = writeback_chunk_size(wb->bdi, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
-		writeback_single_inode(inode, wb, &wbc);
+		/*
+		 * We use I_SYNC to pin the inode in memory. While it is set
+		 * evict_inode() will wait so the inode cannot be freed.
+		 */
+		__writeback_single_inode(inode, wb, &wbc);
 
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
+		spin_lock(&wb->list_lock);
+		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY))
 			wrote++;
-		if (wbc.pages_skipped) {
-			/*
-			 * writeback is not making progress due to locked
-			 * buffers.  Skip this inode for now.
-			 */
-			redirty_tail(inode, wb);
-		}
+		requeue_inode(inode, wb, &wbc);
+		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&wb->list_lock);
-		iput(inode);
-		cond_resched();
-		spin_lock(&wb->list_lock);
+		cond_resched_lock(&wb->list_lock);
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -796,8 +883,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 			trace_writeback_wait(wb->bdi, work);
 			inode = wb_inode(wb->b_more_io.prev);
 			spin_lock(&inode->i_lock);
-			inode_wait_for_writeback(inode, wb);
-			spin_unlock(&inode->i_lock);
+			spin_unlock(&wb->list_lock);
+			/* This function drops i_lock... */
+			inode_sleep_on_writeback(inode);
+			spin_lock(&wb->list_lock);
 		}
 	}
 	spin_unlock(&wb->list_lock);
@@ -1331,7 +1420,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
 int write_inode_now(struct inode *inode, int sync)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-	int ret;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -1343,12 +1431,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	spin_lock(&wb->list_lock);
-	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, wb, &wbc);
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
-	return ret;
+	return writeback_single_inode(inode, wb, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -1365,15 +1448,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-	int ret;
-
-	spin_lock(&wb->list_lock);
-	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, wb, wbc);
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
-	return ret;
+	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
 }
 EXPORT_SYMBOL(sync_inode);