[PATCH v2 6/9] NFSD: check truncate permission under inode lock

From: Chuck Lever <[email protected]>

nfsd_setattr() checks whether a size update needs NFSD_MAY_TRUNC
before it takes inode_lock(). The comparison uses the file size sampled
by that unlocked read, but the actual ATTR_SIZE update is applied later
under inode_lock() by notify_change().

This leaves a TOCTOU window for append-only files. If a client sends a
SETATTR that does not shrink the file at the time of the unlocked
sample, a concurrent append can extend the file before nfsd_setattr()
takes inode_lock(). notify_change() then applies a real truncation
without the NFSD_MAY_TRUNC check that rejects IS_APPEND(inode). The VFS
truncate syscall paths perform their own append-only checks before
calling notify_change(), so NFSD must make this decision against the
locked size it is about to change.

Split the write-count acquisition from the truncation permission check.
Keep get_write_access() before the locked setattr work, then recheck
whether the requested size is below i_size_read(inode) after inode_lock()
has been acquired and before notify_change(ATTR_SIZE). This also avoids
the plain unlocked inode->i_size load.

Fixes: 783112f7401f ("nfsd: special case truncates some more")
Assisted-by: kres:claude-opus-4-7
Reported-by: Chris Mason <[email protected]>
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Jeff Layton <[email protected]>
---
 fs/nfsd/vfs.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7e6468bdc723..07a9a68408ba 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -419,21 +419,22 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 }
 
 static __be32
-nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		struct iattr *iap)
+nfsd_may_truncate(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct iattr *iap)
 {
 	struct inode *inode = d_inode(fhp->fh_dentry);
 
-	if (iap->ia_size < inode->i_size) {
-		__be32 err;
+	if (iap->ia_size >= i_size_read(inode))
+		return nfs_ok;
 
-		err = nfsd_permission(&rqstp->rq_cred,
-				      fhp->fh_export, fhp->fh_dentry,
-				      NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
-		if (err)
-			return err;
-	}
-	return nfserrno(get_write_access(inode));
+	return nfsd_permission(&rqstp->rq_cred, fhp->fh_export, fhp->fh_dentry,
+			       NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+}
+
+static __be32
+nfsd_get_write_access(struct svc_fh *fhp)
+{
+	return nfserrno(get_write_access(d_inode(fhp->fh_dentry)));
 }
 
 static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
@@ -560,12 +561,17 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 * setattr call.
 	 */
 	if (size_change) {
-		err = nfsd_get_write_access(rqstp, fhp, iap);
+		err = nfsd_get_write_access(fhp);
 		if (err)
 			return err;
 	}
 
 	inode_lock(inode);
+	if (size_change) {
+		err = nfsd_may_truncate(rqstp, fhp, iap);
+		if (err)
+			goto out_unlock;
+	}
 	err = fh_fill_pre_attrs(fhp);
 	if (err)
 		goto out_unlock;

-- 
2.54.0