1 files changed, 83 insertions, 40 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b4914a11c3c2..596f35170137 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -205,12 +205,15 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 		nfs_fscache_invalidate(inode, 0);
 	flags &= ~NFS_INO_REVAL_FORCED;
 
-	nfsi->cache_validity |= flags;
+	flags |= nfsi->cache_validity;
+	if (inode->i_mapping->nrpages == 0)
+		flags &= ~NFS_INO_INVALID_DATA;
 
-	if (inode->i_mapping->nrpages == 0) {
-		nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
-		nfs_ooo_clear(nfsi);
-	} else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
+	/* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */
+	smp_store_release(&nfsi->cache_validity, flags);
+
+	if (inode->i_mapping->nrpages == 0 ||
+	    nfsi->cache_validity & NFS_INO_INVALID_DATA) {
 		nfs_ooo_clear(nfsi);
 	}
 	trace_nfs_set_cache_invalid(inode, 0);
@@ -628,23 +631,35 @@ nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr)
 	}
 }
 
+static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid)
+{
+	enum file_time_flags time_flags = 0;
+	unsigned int cache_flags = 0;
+
+	if (ia_valid & ATTR_MTIME) {
+		time_flags |= S_MTIME | S_CTIME;
+		cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+	}
+	if (ia_valid & ATTR_ATIME) {
+		time_flags |= S_ATIME;
+		cache_flags |= NFS_INO_INVALID_ATIME;
+	}
+	inode_update_timestamps(inode, time_flags);
+	NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
 void nfs_update_delegated_atime(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	if (nfs_have_delegated_atime(inode)) {
-		inode_update_timestamps(inode, S_ATIME);
-		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ATIME;
-	}
+	if (nfs_have_delegated_atime(inode))
+		nfs_update_timestamps(inode, ATTR_ATIME);
 	spin_unlock(&inode->i_lock);
 }
 
 void nfs_update_delegated_mtime_locked(struct inode *inode)
 {
-	if (nfs_have_delegated_mtime(inode)) {
-		inode_update_timestamps(inode, S_CTIME | S_MTIME);
-		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_CTIME |
-						  NFS_INO_INVALID_MTIME);
-	}
+	if (nfs_have_delegated_mtime(inode))
+		nfs_update_timestamps(inode, ATTR_MTIME);
 }
 
 void nfs_update_delegated_mtime(struct inode *inode)
@@ -682,15 +697,16 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			attr->ia_valid &= ~ATTR_SIZE;
 	}
 
-	if (nfs_have_delegated_mtime(inode)) {
-		if (attr->ia_valid & ATTR_MTIME) {
-			nfs_update_delegated_mtime(inode);
-			attr->ia_valid &= ~ATTR_MTIME;
-		}
-		if (attr->ia_valid & ATTR_ATIME) {
-			nfs_update_delegated_atime(inode);
-			attr->ia_valid &= ~ATTR_ATIME;
-		}
+	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
+		spin_lock(&inode->i_lock);
+		nfs_update_timestamps(inode, attr->ia_valid);
+		spin_unlock(&inode->i_lock);
+		attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME);
+	} else if (nfs_have_delegated_atime(inode) &&
+		   attr->ia_valid & ATTR_ATIME &&
+		   !(attr->ia_valid & ATTR_MTIME)) {
+		nfs_update_delegated_atime(inode);
+		attr->ia_valid &= ~ATTR_ATIME;
 	}
 
 	/* Optimization: if the end result is no change, don't RPC */
@@ -1408,6 +1424,13 @@ int nfs_clear_invalid_mapping(struct address_space *mapping)
 					 TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		if (ret)
 			goto out;
+		smp_rmb(); /* pairs with smp_wmb() below */
+		if (test_bit(NFS_INO_INVALIDATING, bitlock))
+			continue;
+		/* pairs with nfs_set_cache_invalid()'s smp_store_release() */
+		if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA))
+			goto out;
+		/* Slow-path that double-checks with spinlock held */
 		spin_lock(&inode->i_lock);
 		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
 			spin_unlock(&inode->i_lock);
@@ -1633,6 +1656,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 	fattr->gencount = nfs_inc_attr_generation_counter();
 	fattr->owner_name = NULL;
 	fattr->group_name = NULL;
+	fattr->mdsthreshold = NULL;
 }
 EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
@@ -2461,35 +2485,54 @@ static void nfs_destroy_inodecache(void)
 	kmem_cache_destroy(nfs_inode_cachep);
 }
 
+struct workqueue_struct *nfslocaliod_workqueue;
 struct workqueue_struct *nfsiod_workqueue;
 EXPORT_SYMBOL_GPL(nfsiod_workqueue);
 
 /*
- * start up the nfsiod workqueue
+ * Destroy the nfsiod workqueues
  */
-static int nfsiod_start(void)
+static void nfsiod_stop(void)
 {
 	struct workqueue_struct *wq;
-	dprintk("RPC:       creating workqueue nfsiod\n");
-	wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
-	if (wq == NULL)
-		return -ENOMEM;
-	nfsiod_workqueue = wq;
-	return 0;
+
+	wq = nfsiod_workqueue;
+	if (wq != NULL) {
+		nfsiod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	wq = nfslocaliod_workqueue;
+	if (wq != NULL) {
+		nfslocaliod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#endif /* CONFIG_NFS_LOCALIO */
 }
 
 /*
- * Destroy the nfsiod workqueue
+ * Start the nfsiod workqueues
  */
-static void nfsiod_stop(void)
+static int nfsiod_start(void)
 {
-	struct workqueue_struct *wq;
-
-	wq = nfsiod_workqueue;
-	if (wq == NULL)
-		return;
-	nfsiod_workqueue = NULL;
-	destroy_workqueue(wq);
+	dprintk("RPC:       creating workqueue nfsiod\n");
+	nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+	if (nfsiod_workqueue == NULL)
+		return -ENOMEM;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	/*
+	 * localio writes need to use a normal (non-memreclaim) workqueue.
+	 * When we start getting low on space, XFS goes and calls flush_work() on
+	 * a non-memreclaim work queue, which causes a priority inversion problem.
+	 */
+	dprintk("RPC:       creating workqueue nfslocaliod\n");
+	nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0);
+	if (unlikely(nfslocaliod_workqueue == NULL)) {
+		nfsiod_stop();
+		return -ENOMEM;
+	}
+#endif /* CONFIG_NFS_LOCALIO */
+	return 0;
 }
 
 unsigned int nfs_net_id;