Merge tag 'nfs-for-3.14-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights:

   - Fix several races in nfs_revalidate_mapping
   - NFSv4.1 slot leakage in the pNFS files driver
   - Stable fix for a slot leak in nfs40_sequence_done
   - Don't reject NFSv4 servers that support ACLs with only ALLOW aces"

* tag 'nfs-for-3.14-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: initialize the ACL support bits to zero.
  NFSv4.1: Cleanup
  NFSv4.1: Clean up nfs41_sequence_done
  NFSv4: Fix a slot leak in nfs40_sequence_done
  NFSv4.1 free slot before resending I/O to MDS
  nfs: add memory barriers around NFS_INO_INVALID_DATA and NFS_INO_INVALIDATING
  NFS: Fix races in nfs_revalidate_mapping
  sunrpc: turn warn_gssd() log message into a dprintk()
  NFS: fix the handling of NFS_INO_INVALID_DATA flag in nfs_revalidate_mapping
  nfs: handle servers that support only ALLOW ACE type.

1 files changed, 43 insertions, 8 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ea00b34..28a0a3c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -977,11 +977,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 		if (ret < 0)
 			return ret;
 	}
-	spin_lock(&inode->i_lock);
-	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
+		spin_lock(&inode->i_lock);
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-	spin_unlock(&inode->i_lock);
+		spin_unlock(&inode->i_lock);
+	}
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	nfs_fscache_wait_on_invalidate(inode);
 
@@ -1008,6 +1008,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long *bitlock = &nfsi->flags;
 	int ret = 0;
 
 	/* swapfiles are not supposed to be shared. */
@@ -1019,12 +1020,46 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 		if (ret < 0)
 			goto out;
 	}
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
-		trace_nfs_invalidate_mapping_enter(inode);
-		ret = nfs_invalidate_mapping(inode, mapping);
-		trace_nfs_invalidate_mapping_exit(inode, ret);
+
+	/*
+	 * We must clear NFS_INO_INVALID_DATA first to ensure that
+	 * invalidations that come in while we're shooting down the mappings
+	 * are respected. But, that leaves a race window where one revalidator
+	 * can clear the flag, and then another checks it before the mapping
+	 * gets invalidated. Fix that by serializing access to this part of
+	 * the function.
+	 *
+	 * At the same time, we need to allow other tasks to see whether we
+	 * might be in the middle of invalidating the pages, so we only set
+	 * the bit lock here if it looks like we're going to be doing that.
+	 */
+	for (;;) {
+		ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+				  nfs_wait_bit_killable, TASK_KILLABLE);
+		if (ret)
+			goto out;
+		spin_lock(&inode->i_lock);
+		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+			break;
+		spin_unlock(&inode->i_lock);
+		goto out;
 	}
 
+	set_bit(NFS_INO_INVALIDATING, bitlock);
+	smp_wmb();
+	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+	spin_unlock(&inode->i_lock);
+	trace_nfs_invalidate_mapping_enter(inode);
+	ret = nfs_invalidate_mapping(inode, mapping);
+	trace_nfs_invalidate_mapping_exit(inode, ret);
+
+	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
 out:
 	return ret;
 }