From 1138ce1cf60954d1c0e2d7b4eba5b4df5813fd86 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:31:30 -0700
Subject: sunrpc: fix duplicated word in <linux/sunrpc/cache.h>

Change "time time" to "time expiry_time" to match the field name.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Anna Schumaker <anna.schumaker@netapp.com>
Cc: linux-nfs@vger.kernel.org
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/cache.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 10891b70fc7b..d0965e2997b0 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -45,7 +45,8 @@
  */
 struct cache_head {
 	struct hlist_node	cache_list;
-	time64_t	expiry_time;	/* After time time, don't use the data */
+	time64_t	expiry_time;	/* After time expiry_time, don't use
+					 * the data */
 	time64_t	last_refresh;   /* If CACHE_PENDING, this is when upcall was
 					 * sent, else this is when update was
 					 * received, though it is alway set to
-- 
cgit v1.2.3


From 0bdd4cea12a9fd79a7eb7de8493a5fef54d0eea6 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 7 Jul 2020 21:50:12 +0200
Subject: Replace HTTP links with HTTPS ones: NFS, SUNRPC, and LOCKD clients

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
          If both the HTTP and HTTPS versions
          return 200 OK and serve the same content:
            Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/lockd/mon.c                  | 2 +-
 include/linux/sunrpc/bc_xprt.h  | 2 +-
 include/linux/sunrpc/msg_prot.h | 2 +-
 net/sunrpc/backchannel_rqst.c   | 2 +-
 net/sunrpc/sunrpc.h             | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1eabd91870e6..1d9488cf0534 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -417,7 +417,7 @@ void nsm_release(struct nsm_handle *nsm)
 /*
  * XDR functions for NSM.
  *
- * See http://www.opengroup.org/ for details on the Network
+ * See https://www.opengroup.org/ for details on the Network
  * Status Monitor wire protocol.
  */
 
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index d796058cdff2..f07c334c599f 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index bea40d9f03a1..43f854487539 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -143,7 +143,7 @@ typedef __be32	rpc_fraghdr;
 /*
  * Well-known netids. See:
  *
- *   http://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
+ *   https://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
  */
 #define RPCBIND_NETID_UDP	"udp"
 #define RPCBIND_NETID_TCP	"tcp"
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 195b40c5dae4..3fecad369592 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -5,7 +5,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index f6fe2e6cd65a..2f59464e6524 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-- 
cgit v1.2.3


From c754e137f55e075d6b6ad9b866c32e9aad260a83 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 18 Sep 2020 15:29:59 -0400
Subject: pNFS/flexfiles: Be consistent about mirror index types

A mirror index is always of type u32.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 34 +++++++++++++++++-----------------
 include/linux/nfs_xdr.h                |  4 ++--
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 1edeebd51937..a163533446fa 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
 }
 
 static void
-ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
 }
 
 static void
-ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
-			     int start_idx, int *best_idx,
+			     u32 start_idx, u32 *best_idx,
 			     bool check_device)
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
 	bool fail_return = false;
-	int idx;
+	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
@@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
-				 int start_idx, int *best_idx)
+				 u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
-				   int start_idx, int *best_idx)
+				   u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
-				  int start_idx, int *best_idx)
+				  u32 start_idx, u32 *best_idx)
 {
 	struct nfs4_pnfs_ds *ds;
 
@@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 }
 
 static struct nfs4_pnfs_ds *
-ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx)
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
+			  u32 *best_idx)
 {
 	struct pnfs_layout_segment *lseg = pgio->pg_lseg;
 	struct nfs4_pnfs_ds *ds;
@@ -837,8 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	int ds_idx;
-	u32 i;
+	u32 ds_idx, i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -895,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_pnfs_ds *ds;
-	int i;
+	u32 i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -1039,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
 {
 	u32 idx = hdr->pgio_mirror_idx + 1;
-	int new_idx = 0;
+	u32 new_idx = 0;
 
 	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx))
 		ff_layout_send_layouterror(hdr->lseg);
@@ -1076,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 					   struct nfs4_state *state,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct pnfs_layout_hdr *lo = lseg->pls_layout;
 	struct inode *inode = lo->plh_inode;
@@ -1150,7 +1150,7 @@ reset:
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -1185,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 					struct nfs4_state *state,
 					struct nfs_client *clp,
 					struct pnfs_layout_segment *lseg,
-					int idx)
+					u32 idx)
 {
 	int vers = clp->cl_nfs_mod->rpc_vers->number;
 
@@ -1212,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 }
 
 static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
-					int idx, u64 offset, u64 length,
+					u32 idx, u64 offset, u64 length,
 					u32 *op_status, int opnum, int error)
 {
 	struct nfs4_ff_layout_mirror *mirror;
@@ -1810,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	loff_t offset = hdr->args.offset;
 	int vers;
 	struct nfs_fh *fh;
-	int idx = hdr->pgio_mirror_idx;
+	u32 idx = hdr->pgio_mirror_idx;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9408f3252c8e..69cb46f7b8d2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1611,8 +1611,8 @@ struct nfs_pgio_header {
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
-	int			ds_commit_idx;	/* ds index if ds_clp is set */
-	int			pgio_mirror_idx;/* mirror index in pgio layer */
+	u32			ds_commit_idx;	/* ds index if ds_clp is set */
+	u32			pgio_mirror_idx;/* mirror index in pgio layer */
 };
 
 struct nfs_mds_commit_info {
-- 
cgit v1.2.3


From 76bd5c016ef49683d626a48748ef1764aaf8ba63 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Mon, 14 Sep 2020 17:05:08 -0400
Subject: NFSv4: make cache consistency bitmask dynamic

Client uses static bitmask for GETATTR on CLOSE/WRITE/DELEGRETURN
and ignores the fact that it might have some attributes marked
invalid in its cache. Compared to v3 where all attributes are
retrieved in postop attributes, v4's cache is frequently out of
sync and leads to standalone GETATTRs being sent to the server.

Instead, in addition to the minimum cache consistency attributes
also check cache_validity and adjust the GETATTR request accordingly.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 45 ++++++++++++++++++++++++++++++++++++++++++---
 include/linux/nfs_xdr.h |  6 +++---
 2 files changed, 45 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index aca52e52538f..542961ffa529 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -107,6 +107,9 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
 static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
 		const struct cred *, bool);
 #endif
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+		struct nfs_server *server,
+		struct nfs4_label *label);
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 static inline struct nfs4_label *
@@ -3632,9 +3635,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 
 	if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
 		/* Close-to-open cache consistency revalidation */
-		if (!nfs4_have_delegation(inode, FMODE_READ))
+		if (!nfs4_have_delegation(inode, FMODE_READ)) {
 			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
-		else
+			nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+		} else
 			calldata->arg.bitmask = NULL;
 	}
 
@@ -5360,6 +5364,38 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
 	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+				struct nfs_server *server,
+				struct nfs4_label *label)
+{
+
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	if ((cache_validity & NFS_INO_INVALID_DATA) ||
+		(cache_validity & NFS_INO_REVAL_PAGECACHE) ||
+		(cache_validity & NFS_INO_REVAL_FORCED) ||
+		(cache_validity & NFS_INO_INVALID_OTHER))
+		nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
+
+	if (cache_validity & NFS_INO_INVALID_ATIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+	if (cache_validity & NFS_INO_INVALID_ACCESS)
+		bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
+				FATTR4_WORD1_OWNER_GROUP;
+	if (cache_validity & NFS_INO_INVALID_ACL)
+		bitmask[0] |= FATTR4_WORD0_ACL;
+	if (cache_validity & NFS_INO_INVALID_LABEL)
+		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
+	if (cache_validity & NFS_INO_INVALID_CTIME)
+		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_MTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
+	if (cache_validity & NFS_INO_INVALID_SIZE)
+		bitmask[0] |= FATTR4_WORD0_SIZE;
+	if (cache_validity & NFS_INO_INVALID_BLOCKS)
+		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+}
+
 static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 				  struct rpc_message *msg,
 				  struct rpc_clnt **clnt)
@@ -5369,8 +5405,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 	if (!nfs4_write_need_cache_consistency_data(hdr)) {
 		hdr->args.bitmask = NULL;
 		hdr->res.fattr = NULL;
-	} else
+	} else {
 		hdr->args.bitmask = server->cache_consistency_bitmask;
+		nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+	}
 
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_write_done_cb;
@@ -6406,6 +6444,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
 	data->args.bitmask = server->cache_consistency_bitmask;
+	nfs4_bitmask_adjust(data->args.bitmask, inode, server, NULL);
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 69cb46f7b8d2..0599efd57eb9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -525,7 +525,7 @@ struct nfs_closeargs {
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	u32			share_access;
-	const u32 *		bitmask;
+	u32 *			bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -608,7 +608,7 @@ struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
-	const u32 * bitmask;
+	u32 * bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -648,7 +648,7 @@ struct nfs_pgio_args {
 	union {
 		unsigned int		replen;			/* used by read */
 		struct {
-			const u32 *		bitmask;	/* used by write */
+			u32 *			bitmask;	/* used by write */
 			enum nfs3_stable_how	stable;		/* used by write */
 		};
 	};
-- 
cgit v1.2.3


From cf1f08cac375630af6b6307907a3fc20fcf847c7 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Fri, 17 Apr 2020 11:00:24 -0400
Subject: SUNRPC: Implement a xdr_page_pos() function

I'll need this for READ_PLUS to help figure out the offset where page
data is stored at, but it might also be useful for other things.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5a6a81b7cd9f..25a68dd87ecf 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -240,6 +240,7 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
+extern unsigned int xdr_page_pos(const struct xdr_stream *xdr);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index fa7517c1d125..909920fab93b 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -505,6 +505,19 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+/**
+ * xdr_page_pos - Return the current offset from the start of the xdr pages
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_page_pos(const struct xdr_stream *xdr)
+{
+	unsigned int pos = xdr_stream_pos(xdr);
+
+	WARN_ON(pos < xdr->buf->head[0].iov_len);
+	return pos - xdr->buf->head[0].iov_len;
+}
+EXPORT_SYMBOL_GPL(xdr_page_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From c567552612ece787b178e3b147b5854ad422a836 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:41:22 -0400
Subject: NFS: Add READ_PLUS data segment support

This patch adds client support for decoding a single NFS4_CONTENT_DATA
segment returned by the server. This is the simplest implementation
possible, since it does not account for any hole segments in the reply.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs42xdr.c         | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4client.c       |   2 +
 fs/nfs/nfs4proc.c         |  43 +++++++++++++-
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   2 +-
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |   2 +-
 7 files changed, 187 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index cc50085e151c..930b4ca212c1 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -722,6 +749,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -970,6 +1019,71 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_read_pages(xdr, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	type = be32_to_cpup(p++);
+	if (type == NFS4_CONTENT_DATA)
+		status = decode_read_plus_data(xdr, res, &eof);
+	else
+		return -EINVAL;
+
+	if (status)
+		return status;
+	if (segments > 1)
+		eof = 0;
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1146,6 +1260,33 @@ out:
 	return status;
 }
 
+/*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index daacc78a3d48..be7915c861ce 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f7ef2ca699a5..d09fd3236820 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -70,6 +70,10 @@
 
 #include "nfs4trace.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_BITMASK_SZ		3
@@ -5272,28 +5276,60 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+static bool nfs4_read_plus_not_supported(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
 {
+	struct nfs_server *server = NFS_SERVER(hdr->inode);
+	struct rpc_message *msg = &task->tk_msg;
 
+	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
+	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+		server->caps &= ~NFS_CAP_READ_PLUS;
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+		rpc_restart_call_prepare(task);
+		return true;
+	}
+	return false;
+}
+
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+{
 	dprintk("--> %s\n", __func__);
 
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
 		return -EAGAIN;
+	if (nfs4_read_plus_not_supported(task, hdr))
+		return -EAGAIN;
 	if (task->tk_status > 0)
 		nfs_invalidate_atime(hdr->inode);
 	return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) :
 				    nfs4_read_done_cb(task, hdr);
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	if (server->caps & NFS_CAP_READ_PLUS)
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
+	else
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#else
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_read_done_cb;
-	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+	nfs42_read_plus_support(NFS_SERVER(hdr->inode), msg);
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 }
 
@@ -10215,7 +10251,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
-		| NFS_CAP_LAYOUTERROR,
+		| NFS_CAP_LAYOUTERROR
+		| NFS_CAP_READ_PLUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 3336ea3407a0..c6dbfcae7517 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7615,6 +7615,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
+	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index b8360be141da..9dc7eeac924f 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -551,13 +551,13 @@ enum {
 
 	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LAYOUTERROR,
-
 	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_GETXATTR,
 	NFSPROC4_CLNT_SETXATTR,
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
+	NFSPROC4_CLNT_READ_PLUS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7eae72a8762e..38e60ec742df 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -287,5 +287,6 @@ struct nfs_server {
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
 #define NFS_CAP_XATTR		(1U << 28)
+#define NFS_CAP_READ_PLUS	(1U << 29)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0599efd57eb9..d63cb862d58e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -657,7 +657,7 @@ struct nfs_pgio_args {
 struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
-	__u32			count;
+	__u64			count;
 	__u32			op_status;
 	union {
 		struct {
-- 
cgit v1.2.3


From 84ce182ab85b8ad5002fb1125ba572df99dd0d1c Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:38:53 -0400
Subject: SUNRPC: Add the ability to expand holes in data pages

This patch adds the ability to "read a hole" into a set of XDR data
pages by taking the following steps:

1) Shift all data after the current xdr->p to the right, possibly into
   the tail,
2) Zero the specified range, and
3) Update xdr->p to point beyond the hole.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 25a68dd87ecf..f9636d2a6d54 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 10a88a67206a..1052ccdb4e99 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -390,6 +390,38 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+/**
+ * _zero_pages
+ * @pages: array of pages
+ * @pgbase: beginning page vector address
+ * @len: length
+ */
+static void
+_zero_pages(struct page **pages, size_t pgbase, size_t len)
+{
+	struct page **page;
+	char *vpage;
+	size_t zero;
+
+	page = pages + (pgbase >> PAGE_SHIFT);
+	pgbase &= ~PAGE_MASK;
+
+	do {
+		zero = PAGE_SIZE - pgbase;
+		if (zero > len)
+			zero = len;
+
+		vpage = kmap_atomic(*page);
+		memset(vpage + pgbase, 0, zero);
+		kunmap_atomic(vpage);
+
+		flush_dcache_page(*page);
+		pgbase = 0;
+		page++;
+
+	} while ((len -= zero) != 0);
+}
+
 /**
  * xdr_shrink_bufhead
  * @buf: xdr_buf
@@ -1096,6 +1128,43 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int bytes;
+	unsigned int from;
+	unsigned int truncated = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+
+	if (offset + length + bytes > buf->page_len) {
+		unsigned int shift = (offset + length + bytes) - buf->page_len;
+		unsigned int res = _shift_data_right_tail(buf, from + bytes - shift, shift);
+		truncated = shift - res;
+		xdr->nwords -= XDR_QUADLEN(truncated);
+		bytes -= shift;
+	}
+
+	/* Now move the page data over and zero pages */
+	if (bytes > 0)
+		_shift_data_right_pages(buf->pages,
+					buf->page_base + offset + length,
+					buf->page_base + from,
+					bytes);
+	_zero_pages(buf->pages, buf->page_base + offset, length);
+
+	buf->len += length - (from - offset) - truncated;
+	xdr_set_page(xdr, offset + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_expand_hole);
+
 /**
  * xdr_enter_page - decode data from the XDR page
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From e6ac0accb27c6892b7ebc7799e7ce56b3390a678 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Tue, 21 Apr 2020 11:27:00 -0400
Subject: SUNRPC: Add an xdr_align_data() function

For now, this function simply aligns the data at the beginning of the
pages. This can eventually be expanded to shift data to the correct
offsets when we're ready.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |   1 +
 net/sunrpc/xdr.c           | 121 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index f9636d2a6d54..fe7ff7f5b584 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1052ccdb4e99..3feff529a764 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -19,6 +19,9 @@
 #include <linux/bvec.h>
 #include <trace/events/sunrpc.h>
 
+static void _copy_to_pages(struct page **, size_t, const char *, size_t);
+
+
 /*
  * XDR functions for basic NFS types
  */
@@ -201,6 +204,88 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages);
  * Helper routines for doing 'memmove' like operations on a struct xdr_buf
  */
 
+/**
+ * _shift_data_left_pages
+ * @pages: vector of pages containing both the source and dest memory area.
+ * @pgto_base: page vector address of destination
+ * @pgfrom_base: page vector address of source
+ * @len: number of bytes to copy
+ *
+ * Note: the addresses pgto_base and pgfrom_base are both calculated in
+ *       the same way:
+ *            if a memory area starts at byte 'base' in page 'pages[i]',
+ *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
+ * Alse note: pgto_base must be < pgfrom_base, but the memory areas
+ * 	they point to may overlap.
+ */
+static void
+_shift_data_left_pages(struct page **pages, size_t pgto_base,
+			size_t pgfrom_base, size_t len)
+{
+	struct page **pgfrom, **pgto;
+	char *vfrom, *vto;
+	size_t copy;
+
+	BUG_ON(pgfrom_base <= pgto_base);
+
+	pgto = pages + (pgto_base >> PAGE_SHIFT);
+	pgfrom = pages + (pgfrom_base >> PAGE_SHIFT);
+
+	pgto_base &= ~PAGE_MASK;
+	pgfrom_base &= ~PAGE_MASK;
+
+	do {
+		if (pgto_base >= PAGE_SIZE) {
+			pgto_base = 0;
+			pgto++;
+		}
+		if (pgfrom_base >= PAGE_SIZE){
+			pgfrom_base = 0;
+			pgfrom++;
+		}
+
+		copy = len;
+		if (copy > (PAGE_SIZE - pgto_base))
+			copy = PAGE_SIZE - pgto_base;
+		if (copy > (PAGE_SIZE - pgfrom_base))
+			copy = PAGE_SIZE - pgfrom_base;
+
+		vto = kmap_atomic(*pgto);
+		if (*pgto != *pgfrom) {
+			vfrom = kmap_atomic(*pgfrom);
+			memcpy(vto + pgto_base, vfrom + pgfrom_base, copy);
+			kunmap_atomic(vfrom);
+		} else
+			memmove(vto + pgto_base, vto + pgfrom_base, copy);
+		flush_dcache_page(*pgto);
+		kunmap_atomic(vto);
+
+		pgto_base += copy;
+		pgfrom_base += copy;
+
+	} while ((len -= copy) != 0);
+}
+
+static void
+_shift_data_left_tail(struct xdr_buf *buf, unsigned int pgto, size_t len)
+{
+	struct kvec *tail = buf->tail;
+
+	if (len > tail->iov_len)
+		len = tail->iov_len;
+
+	_copy_to_pages(buf->pages,
+		       buf->page_base + pgto,
+		       (char *)tail->iov_base,
+		       len);
+	tail->iov_len -= len;
+
+	if (tail->iov_len > 0)
+		memmove((char *)tail->iov_base,
+				tail->iov_base + len,
+				tail->iov_len);
+}
+
 /**
  * _shift_data_right_pages
  * @pages: vector of pages containing both the source and dest memory area.
@@ -1128,6 +1213,42 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_align_data(struct xdr_stream *xdr, uint64_t offset, uint32_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int from, bytes;
+	unsigned int shift = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+	if (length < bytes)
+		bytes = length;
+
+	/* Move page data to the left */
+	if (from > offset) {
+		shift = min_t(unsigned int, bytes, buf->page_len - from);
+		_shift_data_left_pages(buf->pages,
+				       buf->page_base + offset,
+				       buf->page_base + from,
+				       shift);
+		bytes -= shift;
+
+		/* Move tail data into the pages, if necessary */
+		if (bytes > 0)
+			_shift_data_left_tail(buf, offset + shift, bytes);
+	}
+
+	xdr->nwords -= XDR_QUADLEN(length);
+	xdr_set_page(xdr, from + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_align_data);
+
 uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
 {
 	struct xdr_buf *buf = xdr->buf;
-- 
cgit v1.2.3