Re: [PATCH v2] nfsd: use short read rather than i_size to set eof

["J. Bruce Fields" <bfields@fieldses.org>]

Possibly overkill, but I think I'll fold in something like this if you
don't see an objection.

--b.

commit 58e18a2a14a0
Author: J. Bruce Fields <bfields@redhat.com>
Date:   Tue Mar 22 14:08:11 2016 -0400

    nfsd: document read eof logic
    
    The choice of checks here is a little subtle, let's document this for
    posterity.
    
    Signed-off-by: J. Bruce Fields <bfields@redhat.com>

diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 83c9abb33e8b..df0f0a86f21d 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -168,8 +168,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 				  &resp->count);
 	if (nfserr == 0) {
 		struct inode	*inode = d_inode(resp->fh.fh_dentry);
-		resp->eof = (cnt > resp->count) ||
-			((argp->offset + resp->count) >= inode->i_size);
+		resp->eof = nfsd_eof_on_read(cnt, resp->count, argp->offset, inode->i_size);
 	}
 
 	RETURN_STATUS(nfserr);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 90232bd7e498..9df898ba648f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3387,8 +3387,8 @@ static __be32 nfsd4_encode_splice_read(
 		return nfserr;
 	}
 
-	eof = (len > maxcount) ||
-		((read->rd_offset + maxcount >= d_inode(read->rd_fhp->fh_dentry)->i_size));
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	*(p++) = htonl(eof);
 	*(p++) = htonl(maxcount);
@@ -3465,8 +3465,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 		return nfserr;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
-	eof = (len > maxcount) ||
-		((read->rd_offset + maxcount >= d_inode(read->rd_fhp->fh_dentry)->i_size));
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	tmp = htonl(eof);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index c11ba316f23f..6244e073c137 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -139,4 +139,24 @@ static inline int nfsd_create_is_exclusive(int createmode)
 	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
+static inline bool nfsd_eof_on_read(long requested, long read,
+				loff_t offset, loff_t size)
+{
+	/* We assume a short read means eof: */
+	if (requested > read)
+		return true;
+	/*
+	 * A non-short read might also reach end of file.  The spec
+	 * still requires us to set eof in that case.
+	 *
+	 * Further operations may have modified the file size since
+	 * the read, so the following check is not atomic with the read.
+	 * The only case we've seen that cause a problem for a client
+	 * is the case where the read returned a count of 0 without
+	 * setting eof.  That case was fixed by the addition of the
+	 * above check.
+	 */
+	return (offset + read >= size);
+}
+
 #endif /* LINUX_NFSD_VFS_H */