NFSv4: include bitmap in nfsv4 get acl data

The NFSv4 bitmap size is unbounded: a server can return an arbitrary
sized bitmap in an FATTR4_WORD0_ACL request.  Replace using the
nfs4_fattr_bitmap_maxsz as a guess to the maximum bitmask returned by a server
with the inclusion of the bitmap (xdr length plus bitmasks) and the acl data
xdr length to the (cached) acl page data.

This is a general solution to commit e5012d1f "NFSv4.1: update
nfs4_fattr_bitmap_maxsz" and fixes hitting a BUG_ON in xdr_shrink_bufhead
when getting ACLs.

Fix a bug in decode_getacl that returned -EINVAL on ACLs > page when getxattr
was called with a NULL buffer, preventing ACL > PAGE_SIZE from being retrieved.

Cc: stable@kernel.org
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

2 files changed, 80 insertions, 47 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index fcc2408..3b10801 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3426,19 +3426,6 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
  */
 #define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
 
-static void buf_to_pages(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
-{
-	const void *p = buf;
-
-	*pgbase = offset_in_page(buf);
-	p -= *pgbase;
-	while (p < buf + buflen) {
-		*(pages++) = virt_to_page(p);
-		p += PAGE_CACHE_SIZE;
-	}
-}
-
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
 {
@@ -3535,9 +3522,19 @@ out:
 	nfs4_set_cached_acl(inode, acl);
 }
 
+/*
+ * The getxattr API returns the required buffer length when called with a
+ * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating
+ * the required buf.  On a NULL buf, we send a page of data to the server
+ * guessing that the ACL request can be serviced by a page. If so, we cache
+ * up to the page of ACL data, and the 2nd call to getxattr is serviced by
+ * the cache. If not so, we throw away the page, and cache the required
+ * length. The next getxattr call will then produce another round trip to
+ * the server, this time with the input buf of the required size.
+ */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES];
+	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -3552,41 +3549,60 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct page *localpage = NULL;
-	int ret;
+	int ret = -ENOMEM, npages, i, acl_len = 0;
 
-	if (buflen < PAGE_SIZE) {
-		/* As long as we're doing a round trip to the server anyway,
-		 * let's be prepared for a page of acl data. */
-		localpage = alloc_page(GFP_KERNEL);
-		resp_buf = page_address(localpage);
-		if (localpage == NULL)
-			return -ENOMEM;
-		args.acl_pages[0] = localpage;
-		args.acl_pgbase = 0;
-		args.acl_len = PAGE_SIZE;
-	} else {
-		resp_buf = buf;
-		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
+	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	/* As long as we're doing a round trip to the server anyway,
+	 * let's be prepared for a page of acl data. */
+	if (npages == 0)
+		npages = 1;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free;
+	}
+	if (npages > 1) {
+		/* for decoding across pages */
+		args.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!args.acl_scratch)
+			goto out_free;
 	}
-	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0);
+	args.acl_len = npages * PAGE_SIZE;
+	args.acl_pgbase = 0;
+	/* Let decode_getfacl know not to fail if the ACL data is larger than
+	 * the page we send as a guess */
+	if (buf == NULL)
+		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
+	resp_buf = page_address(pages[0]);
+
+	dprintk("%s  buf %p buflen %ld npages %d args.acl_len %ld\n",
+		__func__, buf, buflen, npages, args.acl_len);
+	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
+			     &msg, &args.seq_args, &res.seq_res, 0);
 	if (ret)
 		goto out_free;
-	if (res.acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, res.acl_len);
+
+	acl_len = res.acl_len - res.acl_data_offset;
+	if (acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
+		nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+				      acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (res.acl_len > buflen)
+		if (acl_len > buflen)
 			goto out_free;
-		if (localpage)
-			memcpy(buf, resp_buf, res.acl_len);
+		_copy_from_pages(buf, pages, res.acl_data_offset,
+				res.acl_len);
 	}
-	ret = res.acl_len;
+	ret = acl_len;
 out_free:
-	if (localpage)
-		__free_page(localpage);
+	for (i = 0; i < npages; i++)
+		if (pages[i])
+			__free_page(pages[i]);
+	if (args.acl_scratch)
+		__free_page(args.acl_scratch);
 	return ret;
 }
 
@@ -3617,6 +3633,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
+		/* -ENOENT is returned if there is no ACL or if there is an ACL
+		 * but no cached acl data, just the acl length */
 		return ret;
 	return nfs4_get_acl_uncached(inode, buf, buflen);
 }
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e6161b2..dcaf693 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2517,11 +2517,13 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz + 1;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
+	xdr_set_scratch_buffer(xdr, page_address(args->acl_scratch), PAGE_SIZE);
+
 	encode_nops(&hdr);
 }
 
@@ -4957,17 +4959,18 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-		size_t *acl_len)
+			 struct nfs_getaclres *res)
 {
-	__be32 *savep;
+	__be32 *savep, *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
-	*acl_len = 0;
+	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
+	bm_p = xdr->p;
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -4979,18 +4982,30 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		size_t hdrlen;
 		u32 recvd;
 
+		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+		 * are stored with the acl data to handle the problem of
+		 * variable length bitmaps.*/
+		xdr->p = bm_p;
+		res->acl_data_offset = be32_to_cpup(bm_p) + 2;
+		res->acl_data_offset <<= 2;
+
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
 		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
+		attrlen += res->acl_data_offset;
 		recvd = req->rq_rcv_buf.len - hdrlen;
 		if (attrlen > recvd) {
-			dprintk("NFS: server cheating in getattr"
-					" acl reply: attrlen %u > recvd %u\n",
+			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
+				/* getxattr interface called with a NULL buf */
+				res->acl_len = attrlen;
+				goto out;
+			}
+			dprintk("NFS: acl reply: attrlen %u > recvd %u\n",
 					attrlen, recvd);
 			return -EINVAL;
 		}
 		xdr_read_pages(xdr, attrlen);
-		*acl_len = attrlen;
+		res->acl_len = attrlen;
 	} else
 		status = -EOPNOTSUPP;
 
@@ -6028,7 +6043,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, &res->acl_len);
+	status = decode_getacl(xdr, rqstp, res);
 
 out:
 	return status;