NFSv4.2: Rework scratch handling for READ_PLUS (again)

commit 303a780520 upstream.

I found that the read code might send multiple requests using the same
nfs_pgio_header, but nfs4_proc_read_setup() is only called once. This is
how we ended up occasionally double-freeing the scratch buffer, but also
means we set a NULL pointer but non-zero length to the xdr scratch
buffer. This results in an oops the first time decoding needs to copy
something to scratch, which frequently happens when decoding READ_PLUS
hole segments.

I fix this by moving scratch handling into the pageio read code. I
provide a function to allocate scratch space for decoding read replies,
and free the scratch buffer when the nfs_pgio_header is freed.

Fixes: fbd2a05f29 (NFSv4.2: Rework scratch handling for READ_PLUS)
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/nfs/internal.h

@@ -484,6 +484,7 @@ struct nfs_pgio_completion_ops;
 extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, bool force_mds,
 			const struct nfs_pgio_completion_ops *compl_ops);
+extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size);
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 

fs/nfs/nfs42.h

@@ -13,6 +13,7 @@
  * more? Need to consider not to pre-alloc too much for a compound.
  */
 #define PNFS_LAYOUTSTATS_MAXDEV (4)
+#define READ_PLUS_SCRATCH_SIZE (16)
 
 /* nfs4.2proc.c */
 #ifdef CONFIG_NFS_V4_2

fs/nfs/nfs42xdr.c

@@ -1351,7 +1351,7 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
 	struct compound_hdr hdr;
 	int status;
 
-	xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch));
+	xdr_set_scratch_buffer(xdr, res->scratch, READ_PLUS_SCRATCH_SIZE);
 
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)

fs/nfs/nfs4proc.c

@@ -5444,18 +5444,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
 	return false;
 }
 
-static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr)
-{
-	if (hdr->res.scratch) {
-		kfree(hdr->res.scratch);
-		hdr->res.scratch = NULL;
-	}
-}
-
 static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	nfs4_read_plus_scratch_free(hdr);
-
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
@@ -5475,8 +5465,7 @@ static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr,
 	/* Note: We don't use READ_PLUS with pNFS yet */
 	if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) {
 		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
-		hdr->res.scratch = kmalloc(32, GFP_KERNEL);
+		return nfs_read_alloc_scratch(hdr, READ_PLUS_SCRATCH_SIZE);
-		return hdr->res.scratch != NULL;
 	}
 	return false;
 }

fs/nfs/read.c

@@ -47,6 +47,8 @@ static struct nfs_pgio_header *nfs_readhdr_alloc(void)
 
 static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
 {
+	if (rhdr->res.scratch != NULL)
+		kfree(rhdr->res.scratch);
 	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
 
@@ -109,6 +111,14 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
+bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size)
+{
+	WARN_ON(hdr->res.scratch != NULL);
+	hdr->res.scratch = kmalloc(size, GFP_KERNEL);
+	return hdr->res.scratch != NULL;
+}
+EXPORT_SYMBOL_GPL(nfs_read_alloc_scratch);
+
 static void nfs_readpage_release(struct nfs_page *req, int error)
 {
 	struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);