From: Jeff Mahoney <jeffm@suse.com>
Subject: btrfs: qgroups, fix rescan worker running races
Patch-mainline: Submitted, linux-btrfs. v3 on 2 May 2018, this is v4.
References: bsc#1091101

Commit 8d9eddad194 (Btrfs: fix qgroup rescan worker initialization)
fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
ended up reintroducing the hang-on-unmount bug that the commit it
intended to fix addressed.

The race this time is between qgroup_rescan_init setting
->qgroup_rescan_running = true and the worker starting.  There are
many scenarios where we initialize the worker and never start it.  The
completion btrfs_ioctl_quota_rescan_wait waits for will never come.
This can happen even without involving error handling, since mounting
the file system read-only returns between initializing the worker and
queueing it.

The right place to do it is when we're queuing the worker.  The flag
really just means that btrfs_ioctl_quota_rescan_wait should wait for
a completion.

Since the BTRFS_QGROUP_STATUS_FLAG_RESCAN flag is overloaded to
refer to both runtime behavior and on-disk state, we introduce a new
fs_info->qgroup_rescan_ready to indicate that we're initialized and
waiting to start.

This patch introduces a new helper, queue_rescan_worker, that handles
most of the initialization, the two flags, and queuing the worker,
including races with unmount.

While we're at it, ->qgroup_rescan_running is protected only by the
->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
to take the spinlock too.

Fixes: 8d9eddad194 (Btrfs: fix qgroup rescan worker initialization)
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/ctree.h  |    2 +
 fs/btrfs/ioctl.c  |    2 -
 fs/btrfs/qgroup.c |   98 +++++++++++++++++++++++++++++++-----------------------
 3 files changed, 61 insertions(+), 41 deletions(-)

--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1087,6 +1087,8 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
 	struct btrfs_work qgroup_rescan_work;
+	/* qgroup rescan worker is running or queued to run */
+	bool qgroup_rescan_ready;
 	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
 
 	/* filesystem state */
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5147,7 +5147,7 @@ static long btrfs_ioctl_quota_rescan_sta
 	if (!qsa)
 		return -ENOMEM;
 
-	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+	if (fs_info->qgroup_rescan_ready || fs_info->qgroup_rescan_running) {
 		qsa->flags = 1;
 		qsa->progress = fs_info->qgroup_rescan_progress.objectid;
 	}
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -178,6 +178,7 @@ static int
 qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		   int init_flags);
 static void qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info);
+static void btrfs_qgroup_rescan_worker(struct btrfs_work *work);
 
 /* must be called with qgroup_ioctl_lock held */
 static struct btrfs_qgroup *find_qgroup_rb(struct btrfs_fs_info *fs_info,
@@ -2009,7 +2010,7 @@ btrfs_qgroup_account_extent(struct btrfs
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+	if (fs_info->qgroup_rescan_ready || fs_info->qgroup_rescan_running) {
 		if (fs_info->qgroup_rescan_progress.objectid <= bytenr) {
 			mutex_unlock(&fs_info->qgroup_rescan_lock);
 			ret = 0;
@@ -2113,6 +2114,46 @@ cleanup:
 	return ret;
 }
 
+static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
+{
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	if (btrfs_fs_closing(fs_info)) {
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return;
+	}
+
+	if (WARN_ON(!fs_info->qgroup_rescan_ready)) {
+		btrfs_warn(fs_info, "rescan worker not ready");
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return;
+	}
+	fs_info->qgroup_rescan_ready = false;
+
+	if (WARN_ON(fs_info->qgroup_rescan_running)) {
+		btrfs_warn(fs_info, "rescan worker already queued");
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return;
+	}
+
+	/*
+	 * Being queued is enough for btrfs_qgroup_wait_for_completion
+	 * to need to wait.
+	 */
+	fs_info->qgroup_rescan_running = true;
+	init_completion(&fs_info->qgroup_rescan_completion);
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
+	memset(&fs_info->qgroup_rescan_work, 0,
+	       sizeof(fs_info->qgroup_rescan_work));
+
+	btrfs_init_work(&fs_info->qgroup_rescan_work,
+			btrfs_qgroup_rescan_helper,
+			btrfs_qgroup_rescan_worker, NULL, NULL);
+
+	btrfs_queue_work(fs_info->qgroup_rescan_workers,
+			 &fs_info->qgroup_rescan_work);
+}
+
 /*
  * called from commit_transaction. Writes all changed qgroups to disk.
  */
@@ -2166,8 +2207,7 @@ int btrfs_run_qgroups(struct btrfs_trans
 		ret = qgroup_rescan_init(fs_info, 0, 1);
 		if (!ret) {
 			qgroup_rescan_zero_tracking(fs_info);
-			btrfs_queue_work(fs_info->qgroup_rescan_workers,
-					 &fs_info->qgroup_rescan_work);
+			queue_rescan_worker(fs_info);
 		}
 		ret = 0;
 	}
@@ -2682,6 +2722,10 @@ static void btrfs_qgroup_rescan_worker(s
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
 	err = 0;
 	while (!err && !btrfs_fs_closing(fs_info)) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
@@ -2760,47 +2804,27 @@ qgroup_rescan_init(struct btrfs_fs_info
 {
 	int ret = 0;
 
-	if (!init_flags &&
-	    (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) ||
-	     !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))) {
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 		ret = -EINVAL;
 		goto err;
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	spin_lock(&fs_info->qgroup_lock);
-
-	if (init_flags) {
-		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
-			ret = -EINPROGRESS;
-		else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
-			ret = -EINVAL;
-
-		if (ret) {
-			spin_unlock(&fs_info->qgroup_lock);
-			mutex_unlock(&fs_info->qgroup_rescan_lock);
-			goto err;
-		}
-		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	if (fs_info->qgroup_rescan_ready || fs_info->qgroup_rescan_running) {
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		ret = -EINPROGRESS;
+		goto err;
 	}
 
 	memset(&fs_info->qgroup_rescan_progress, 0,
 		sizeof(fs_info->qgroup_rescan_progress));
 	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
-	init_completion(&fs_info->qgroup_rescan_completion);
-	fs_info->qgroup_rescan_running = true;
+	fs_info->qgroup_rescan_ready = true;
 
-	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	memset(&fs_info->qgroup_rescan_work, 0,
-	       sizeof(fs_info->qgroup_rescan_work));
-	btrfs_init_work(&fs_info->qgroup_rescan_work,
-			btrfs_qgroup_rescan_helper,
-			btrfs_qgroup_rescan_worker, NULL, NULL);
-
-	if (ret) {
 err:
+	if (ret) {
 		btrfs_info(fs_info, "qgroup_rescan_init failed with %d", ret);
 		return ret;
 	}
@@ -2861,9 +2885,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info
 
 	qgroup_rescan_zero_tracking(fs_info);
 
-	btrfs_queue_work(fs_info->qgroup_rescan_workers,
-			 &fs_info->qgroup_rescan_work);
-
+	queue_rescan_worker(fs_info);
 	return 0;
 }
 
@@ -2874,9 +2896,7 @@ int btrfs_qgroup_wait_for_completion(str
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	spin_lock(&fs_info->qgroup_lock);
 	running = fs_info->qgroup_rescan_running;
-	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
 	if (!running)
@@ -2895,12 +2915,10 @@ int btrfs_qgroup_wait_for_completion(str
  * this is only called from open_ctree where we're still single threaded, thus
  * locking is omitted here.
  */
-void
-btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
+void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
 {
-	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
-		btrfs_queue_work(fs_info->qgroup_rescan_workers,
-				 &fs_info->qgroup_rescan_work);
+	if (fs_info->qgroup_rescan_ready)
+		queue_rescan_worker(fs_info);
 }
 
 /*