Merge tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Features:

   - NFSv3: Add emulation of lookupp() to improve open_by_filehandle()
     support

   - A series of patches to improve readdir performance, particularly
     with large directories

   - Basic support for using NFS/RDMA with the pNFS files and flexfiles
     drivers

   - Micro-optimisations for RDMA

   - RDMA tracing improvements

  Bugfixes:

   - Fix a long standing bug with xs_read_xdr_buf() when receiving
     partial pages (Dan Aloni)

   - Various fixes for getxattr and listxattr, when used over non-TCP
     transports

   - Fixes for containerised NFS from Sargun Dhillon

   - switch nfsiod to be an UNBOUND workqueue (Neil Brown)

   - READDIR should not ask for security label information if there is
     no LSM policy (Olga Kornievskaia)

   - Avoid using interval-based rebinding with TCP in lockd (Calum
     Mackay)

   - A series of RPC and NFS layer fixes to support the NFSv4.2
     READ_PLUS code

   - A couple of fixes for pnfs/flexfiles read failover

  Cleanups:

   - Various cleanups for the SUNRPC xdr code in conjunction with the
     READ_PLUS fixes"

* tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
  NFS/pNFS: Fix a typo in ff_layout_resend_pnfs_read()
  pNFS/flexfiles: Avoid spurious layout returns in ff_layout_choose_ds_for_read
  NFSv4/pnfs: Add tracing for the deviceid cache
  fs/lockd: convert comma to semicolon
  NFSv4.2: fix error return on memory allocation failure
  NFSv4.2/pnfs: Don't use READ_PLUS with pNFS yet
  NFSv4.2: Deal with potential READ_PLUS data extent buffer overflow
  NFSv4.2: Don't error when exiting early on a READ_PLUS buffer overflow
  NFSv4.2: Handle hole lengths that exceed the READ_PLUS read buffer
  NFSv4.2: decode_read_plus_hole() needs to check the extent offset
  NFSv4.2: decode_read_plus_data() must skip padding after data segment
  NFSv4.2: Ensure we always reset the result->count in decode_read_plus()
  SUNRPC: When expanding the buffer, we may need grow the sparse pages
  SUNRPC: Cleanup - constify a number of xdr_buf helpers
  SUNRPC: Clean up open coded setting of the xdr_stream 'nwords' field
  SUNRPC: _copy_to/from_pages() now check for zero length
  SUNRPC: Cleanup xdr_shrink_bufhead()
  SUNRPC: Fix xdr_expand_hole()
  SUNRPC: Fixes for xdr_align_data()
  SUNRPC: _shift_data_left/right_pages should check the shift length
  ...

13 files changed, 769 insertions, 453 deletions

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 3259120462ed..612f0a641f4c 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1251,10 +1251,7 @@ void rpc_prepare_reply_pages(struct rpc_rqst *req, struct page **pages,
 			     unsigned int base, unsigned int len,
 			     unsigned int hdrsize)
 {
-	/* Subtract one to force an extra word of buffer space for the
-	 * payload's XDR pad to fall into the rcv_buf's tail iovec.
-	 */
-	hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign - 1;
+	hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign;
 
 	xdr_inline_pages(&req->rq_rcv_buf, hdrsize << 2, pages, base, len);
 	trace_rpc_xdr_reply_pages(req->rq_task, &req->rq_rcv_buf);
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index fd9bca242724..56029e3af6ff 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -128,13 +128,13 @@ static int do_xprt_debugfs(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *n
 		return 0;
 	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
 		       xprt->debugfs->d_name.name);
-	if (len > sizeof(name))
+	if (len >= sizeof(name))
 		return -1;
 	if (*nump == 0)
 		strcpy(link, "xprt");
 	else {
 		len = snprintf(link, sizeof(link), "xprt%d", *nump);
-		if (len > sizeof(link))
+		if (len >= sizeof(link))
 			return -1;
 	}
 	debugfs_create_symlink(link, clnt->cl_debugfs, name);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index f06d7c315017..cf702a5f7fe5 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -676,6 +676,23 @@ struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *queue)
 EXPORT_SYMBOL_GPL(rpc_wake_up_next);
 
 /**
+ * rpc_wake_up_locked - wake up all rpc_tasks
+ * @queue: rpc_wait_queue on which the tasks are sleeping
+ *
+ */
+static void rpc_wake_up_locked(struct rpc_wait_queue *queue)
+{
+	struct rpc_task *task;
+
+	for (;;) {
+		task = __rpc_find_next_queued(queue);
+		if (task == NULL)
+			break;
+		rpc_wake_up_task_queue_locked(queue, task);
+	}
+}
+
+/**
  * rpc_wake_up - wake up all rpc_tasks
  * @queue: rpc_wait_queue on which the tasks are sleeping
  *
@@ -683,25 +700,28 @@ EXPORT_SYMBOL_GPL(rpc_wake_up_next);
  */
 void rpc_wake_up(struct rpc_wait_queue *queue)
 {
-	struct list_head *head;
-
 	spin_lock(&queue->lock);
-	head = &queue->tasks[queue->maxpriority];
+	rpc_wake_up_locked(queue);
+	spin_unlock(&queue->lock);
+}
+EXPORT_SYMBOL_GPL(rpc_wake_up);
+
+/**
+ * rpc_wake_up_status_locked - wake up all rpc_tasks and set their status value.
+ * @queue: rpc_wait_queue on which the tasks are sleeping
+ * @status: status value to set
+ */
+static void rpc_wake_up_status_locked(struct rpc_wait_queue *queue, int status)
+{
+	struct rpc_task *task;
+
 	for (;;) {
-		while (!list_empty(head)) {
-			struct rpc_task *task;
-			task = list_first_entry(head,
-					struct rpc_task,
-					u.tk_wait.list);
-			rpc_wake_up_task_queue_locked(queue, task);
-		}
-		if (head == &queue->tasks[0])
+		task = __rpc_find_next_queued(queue);
+		if (task == NULL)
 			break;
-		head--;
+		rpc_wake_up_task_queue_set_status_locked(queue, task, status);
 	}
-	spin_unlock(&queue->lock);
 }
-EXPORT_SYMBOL_GPL(rpc_wake_up);
 
 /**
  * rpc_wake_up_status - wake up all rpc_tasks and set their status value.
@@ -712,23 +732,8 @@ EXPORT_SYMBOL_GPL(rpc_wake_up);
  */
 void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 {
-	struct list_head *head;
-
 	spin_lock(&queue->lock);
-	head = &queue->tasks[queue->maxpriority];
-	for (;;) {
-		while (!list_empty(head)) {
-			struct rpc_task *task;
-			task = list_first_entry(head,
-					struct rpc_task,
-					u.tk_wait.list);
-			task->tk_status = status;
-			rpc_wake_up_task_queue_locked(queue, task);
-		}
-		if (head == &queue->tasks[0])
-			break;
-		head--;
-	}
+	rpc_wake_up_status_locked(queue, status);
 	spin_unlock(&queue->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_status);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 757560a3b06b..3964ff74ee51 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -123,8 +123,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
  * @len: length of string, in bytes
  *
  */
-void
-xdr_terminate_string(struct xdr_buf *buf, const u32 len)
+void xdr_terminate_string(const struct xdr_buf *buf, const u32 len)
 {
 	char *kaddr;
 
@@ -134,8 +133,7 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len)
 }
 EXPORT_SYMBOL_GPL(xdr_terminate_string);
 
-size_t
-xdr_buf_pagecount(struct xdr_buf *buf)
+size_t xdr_buf_pagecount(const struct xdr_buf *buf)
 {
 	if (!buf->page_len)
 		return 0;
@@ -193,9 +191,6 @@ xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset,
 
 	tail->iov_base = buf + offset;
 	tail->iov_len = buflen - offset;
-	if ((xdr->page_len & 3) == 0)
-		tail->iov_len -= sizeof(__be32);
-
 	xdr->buflen += len;
 }
 EXPORT_SYMBOL_GPL(xdr_inline_pages);
@@ -228,6 +223,9 @@ _shift_data_left_pages(struct page **pages, size_t pgto_base,
 
 	BUG_ON(pgfrom_base <= pgto_base);
 
+	if (!len)
+		return;
+
 	pgto = pages + (pgto_base >> PAGE_SHIFT);
 	pgfrom = pages + (pgfrom_base >> PAGE_SHIFT);
 
@@ -266,26 +264,6 @@ _shift_data_left_pages(struct page **pages, size_t pgto_base,
 	} 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.
@@ -310,6 +288,9 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base,
 
 	BUG_ON(pgto_base <= pgfrom_base);
 
+	if (!len)
+		return;
+
 	pgto_base += len;
 	pgfrom_base += len;
 
@@ -351,46 +332,6 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base,
 	} while ((len -= copy) != 0);
 }
 
-static unsigned int
-_shift_data_right_tail(struct xdr_buf *buf, unsigned int pgfrom, size_t len)
-{
-	struct kvec *tail = buf->tail;
-	unsigned int tailbuf_len;
-	unsigned int result = 0;
-	size_t copy;
-
-	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
-
-	/* Shift the tail first */
-	if (tailbuf_len != 0) {
-		unsigned int free_space = tailbuf_len - tail->iov_len;
-
-		if (len < free_space)
-			free_space = len;
-		if (len > free_space)
-			len = free_space;
-
-		tail->iov_len += free_space;
-		copy = len;
-
-		if (tail->iov_len > len) {
-			char *p = (char *)tail->iov_base + len;
-			memmove(p, tail->iov_base, tail->iov_len - free_space);
-			result += tail->iov_len - free_space;
-		} else
-			copy = tail->iov_len;
-
-		/* Copy from the inlined pages into the tail */
-		_copy_from_pages((char *)tail->iov_base,
-					 buf->pages,
-					 buf->page_base + pgfrom,
-					 copy);
-		result += copy;
-	}
-
-	return result;
-}
-
 /**
  * _copy_to_pages
  * @pages: array of pages
@@ -408,6 +349,9 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len)
 	char *vto;
 	size_t copy;
 
+	if (!len)
+		return;
+
 	pgto = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
 
@@ -452,6 +396,9 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 	char *vfrom;
 	size_t copy;
 
+	if (!len)
+		return;
+
 	pgfrom = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
 
@@ -475,18 +422,42 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+static void xdr_buf_iov_zero(const struct kvec *iov, unsigned int base,
+			     unsigned int len)
+{
+	if (base >= iov->iov_len)
+		return;
+	if (len > iov->iov_len - base)
+		len = iov->iov_len - base;
+	memset(iov->iov_base + base, 0, len);
+}
+
 /**
- * _zero_pages
- * @pages: array of pages
- * @pgbase: beginning page vector address
+ * xdr_buf_pages_zero
+ * @buf: xdr_buf
+ * @pgbase: beginning offset
  * @len: length
  */
-static void
-_zero_pages(struct page **pages, size_t pgbase, size_t len)
+static void xdr_buf_pages_zero(const struct xdr_buf *buf, unsigned int pgbase,
+			       unsigned int len)
 {
+	struct page **pages = buf->pages;
 	struct page **page;
 	char *vpage;
-	size_t zero;
+	unsigned int zero;
+
+	if (!len)
+		return;
+	if (pgbase >= buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, pgbase - buf->page_len, len);
+		return;
+	}
+	if (pgbase + len > buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, 0, pgbase + len - buf->page_len);
+		len = buf->page_len - pgbase;
+	}
+
+	pgbase += buf->page_base;
 
 	page = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
@@ -507,122 +478,367 @@ _zero_pages(struct page **pages, size_t pgbase, size_t len)
 	} while ((len -= zero) != 0);
 }
 
+static unsigned int xdr_buf_pages_fill_sparse(const struct xdr_buf *buf,
+					      unsigned int buflen, gfp_t gfp)
+{
+	unsigned int i, npages, pagelen;
+
+	if (!(buf->flags & XDRBUF_SPARSE_PAGES))
+		return buflen;
+	if (buflen <= buf->head->iov_len)
+		return buflen;
+	pagelen = buflen - buf->head->iov_len;
+	if (pagelen > buf->page_len)
+		pagelen = buf->page_len;
+	npages = (pagelen + buf->page_base + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	for (i = 0; i < npages; i++) {
+		if (!buf->pages[i])
+			continue;
+		buf->pages[i] = alloc_page(gfp);
+		if (likely(buf->pages[i]))
+			continue;
+		buflen -= pagelen;
+		pagelen = i << PAGE_SHIFT;
+		if (pagelen > buf->page_base)
+			buflen += pagelen - buf->page_base;
+		break;
+	}
+	return buflen;
+}
+
+static void xdr_buf_try_expand(struct xdr_buf *buf, unsigned int len)
+{
+	struct kvec *head = buf->head;
+	struct kvec *tail = buf->tail;
+	unsigned int sum = head->iov_len + buf->page_len + tail->iov_len;
+	unsigned int free_space, newlen;
+
+	if (sum > buf->len) {
+		free_space = min_t(unsigned int, sum - buf->len, len);
+		newlen = xdr_buf_pages_fill_sparse(buf, buf->len + free_space,
+						   GFP_KERNEL);
+		free_space = newlen - buf->len;
+		buf->len = newlen;
+		len -= free_space;
+		if (!len)
+			return;
+	}
+
+	if (buf->buflen > sum) {
+		/* Expand the tail buffer */
+		free_space = min_t(unsigned int, buf->buflen - sum, len);
+		tail->iov_len += free_space;
+		buf->len += free_space;
+	}
+}
+
+static void xdr_buf_tail_copy_right(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+
+	if (to >= tail->iov_len)
+		return;
+	if (len + to > tail->iov_len)
+		len = tail->iov_len - to;
+	memmove(tail->iov_base + to, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+	unsigned int pglen = 0;
+	unsigned int talen = 0, tato = 0;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	if (to >= buf->page_len) {
+		tato = to - buf->page_len;
+		if (tail->iov_len >= len + tato)
+			talen = len;
+		else if (tail->iov_len > tato)
+			talen = tail->iov_len - tato;
+	} else if (len + to >= buf->page_len) {
+		pglen = buf->page_len - to;
+		talen = len - pglen;
+		if (talen > tail->iov_len)
+			talen = tail->iov_len;
+	} else
+		pglen = len;
+
+	_copy_from_pages(tail->iov_base + tato, buf->pages,
+			 buf->page_base + base + pglen, talen);
+	_shift_data_right_pages(buf->pages, buf->page_base + to,
+				buf->page_base + base, pglen);
+}
+
+static void xdr_buf_head_copy_right(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	const struct kvec *head = buf->head;
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+	unsigned int pglen = 0, pgto = 0;
+	unsigned int talen = 0, tato = 0;
+
+	if (base >= head->iov_len)
+		return;
+	if (len > head->iov_len - base)
+		len = head->iov_len - base;
+	if (to >= buf->page_len + head->iov_len) {
+		tato = to - buf->page_len - head->iov_len;
+		talen = len;
+	} else if (to >= head->iov_len) {
+		pgto = to - head->iov_len;
+		pglen = len;
+		if (pgto + pglen > buf->page_len) {
+			talen = pgto + pglen - buf->page_len;
+			pglen -= talen;
+		}
+	} else {
+		pglen = len - to;
+		if (pglen > buf->page_len) {
+			talen = pglen - buf->page_len;
+			pglen = buf->page_len;
+		}
+	}
+
+	len -= talen;
+	base += len;
+	if (talen + tato > tail->iov_len)
+		talen = tail->iov_len > tato ? tail->iov_len - tato : 0;
+	memcpy(tail->iov_base + tato, head->iov_base + base, talen);
+
+	len -= pglen;
+	base -= pglen;
+	_copy_to_pages(buf->pages, buf->page_base + pgto, head->iov_base + base,
+		       pglen);
+
+	base -= len;
+	memmove(head->iov_base + to, head->iov_base + base, len);
+}
+
+static void xdr_buf_tail_shift_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len || !shift || !len)
+		return;
+	xdr_buf_tail_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_right(const struct xdr_buf *buf,
+				      unsigned int base, unsigned int len,
+				      unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_right(buf, base - buf->page_len, len, shift);
+		return;
+	}
+	if (base + len > buf->page_len)
+		xdr_buf_tail_shift_right(buf, 0, base + len - buf->page_len,
+					 shift);
+	xdr_buf_pages_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_head_shift_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *head = buf->head;
+
+	if (!shift)
+		return;
+	if (base >= head->iov_len) {
+		xdr_buf_pages_shift_right(buf, head->iov_len - base, len,
+					  shift);
+		return;
+	}
+	if (base + len > head->iov_len)
+		xdr_buf_pages_shift_right(buf, 0, base + len - head->iov_len,
+					  shift);
+	xdr_buf_head_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_tail_copy_left(const struct xdr_buf *buf, unsigned int base,
+				   unsigned int len, unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len)
+		return;
+	if (len > tail->iov_len - base)
+		len = tail->iov_len - base;
+	/* Shift data into head */
+	if (shift > buf->page_len + base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto =
+			head->iov_len + buf->page_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + buf->page_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		memcpy(head->iov_base + hdto, tail->iov_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	/* Shift data into pages */
+	if (shift > base) {
+		unsigned int pgto = buf->page_len + base - shift;
+		unsigned int pglen = len;
+
+		if (pgto + pglen > buf->page_len)
+			pglen = buf->page_len - pgto;
+		_copy_to_pages(buf->pages, buf->page_base + pgto,
+			       tail->iov_base + base, pglen);
+		base += pglen;
+		len -= pglen;
+		if (!len)
+			return;
+	}
+	memmove(tail->iov_base + base - shift, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	unsigned int pgto;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	/* Shift data into head */
+	if (shift > base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto = head->iov_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		_copy_from_pages(head->iov_base + hdto, buf->pages,
+				 buf->page_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	pgto = base - shift;
+	_shift_data_left_pages(buf->pages, buf->page_base + pgto,
+			       buf->page_base + base, len);
+}
+
+static void xdr_buf_tail_shift_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	xdr_buf_tail_copy_left(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_left(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_left(buf, base - buf->page_len, len, shift);
+		return;
+	}
+	xdr_buf_pages_copy_left(buf, base, len, shift);
+	len += base;
+	if (len <= buf->page_len)
+		return;
+	xdr_buf_tail_copy_left(buf, 0, len - buf->page_len, shift);
+}
+
 /**
  * xdr_shrink_bufhead
  * @buf: xdr_buf
- * @len: bytes to remove from buf->head[0]
+ * @len: new length of buf->head[0]
  *
- * Shrinks XDR buffer's header kvec buf->head[0] by
+ * Shrinks XDR buffer's header kvec buf->head[0], setting it to
  * 'len' bytes. The extra data is not lost, but is instead
  * moved into the inlined pages and/or the tail.
  */
-static unsigned int
-xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
+static unsigned int xdr_shrink_bufhead(struct xdr_buf *buf, unsigned int len)
 {
-	struct kvec *head, *tail;
-	size_t copy, offs;
-	unsigned int pglen = buf->page_len;
-	unsigned int result;
-
-	result = 0;
-	tail = buf->tail;
-	head = buf->head;
+	struct kvec *head = buf->head;
+	unsigned int shift, buflen = max(buf->len, len);
 
 	WARN_ON_ONCE(len > head->iov_len);
-	if (len > head->iov_len)
-		len = head->iov_len;
-
-	/* Shift the tail first */
-	if (tail->iov_len != 0) {
-		if (tail->iov_len > len) {
-			copy = tail->iov_len - len;
-			memmove((char *)tail->iov_base + len,
-					tail->iov_base, copy);
-			result += copy;
-		}
-		/* Copy from the inlined pages into the tail */
-		copy = len;
-		if (copy > pglen)
-			copy = pglen;
-		offs = len - copy;
-		if (offs >= tail->iov_len)
-			copy = 0;
-		else if (copy > tail->iov_len - offs)
-			copy = tail->iov_len - offs;
-		if (copy != 0) {
-			_copy_from_pages((char *)tail->iov_base + offs,
-					buf->pages,
-					buf->page_base + pglen + offs - len,
-					copy);
-			result += copy;
-		}
-		/* Do we also need to copy data from the head into the tail ? */
-		if (len > pglen) {
-			offs = copy = len - pglen;
-			if (copy > tail->iov_len)
-				copy = tail->iov_len;
-			memcpy(tail->iov_base,
-					(char *)head->iov_base +
-					head->iov_len - offs,
-					copy);
-			result += copy;
-		}
-	}
-	/* Now handle pages */
-	if (pglen != 0) {
-		if (pglen > len)
-			_shift_data_right_pages(buf->pages,
-					buf->page_base + len,
-					buf->page_base,
-					pglen - len);
-		copy = len;
-		if (len > pglen)
-			copy = pglen;
-		_copy_to_pages(buf->pages, buf->page_base,
-				(char *)head->iov_base + head->iov_len - len,
-				copy);
-		result += copy;
+	if (head->iov_len > buflen) {
+		buf->buflen -= head->iov_len - buflen;
+		head->iov_len = buflen;
 	}
-	head->iov_len -= len;
-	buf->buflen -= len;
-	/* Have we truncated the message? */
-	if (buf->len > buf->buflen)
-		buf->len = buf->buflen;
-
-	return result;
+	if (len >= head->iov_len)
+		return 0;
+	shift = head->iov_len - len;
+	xdr_buf_try_expand(buf, shift);
+	xdr_buf_head_shift_right(buf, len, buflen - len, shift);
+	head->iov_len = len;
+	buf->buflen -= shift;
+	buf->len -= shift;
+	return shift;
 }
 
 /**
- * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes
+ * xdr_shrink_pagelen - shrinks buf->pages to @len bytes
  * @buf: xdr_buf
- * @len: bytes to remove from buf->pages
+ * @len: new page buffer length
  *
  * The extra data is not lost, but is instead moved into buf->tail.
  * Returns the actual number of bytes moved.
  */
-static unsigned int
-xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
+static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, unsigned int len)
 {
-	unsigned int pglen = buf->page_len;
-	unsigned int result;
+	unsigned int shift, buflen = buf->len - buf->head->iov_len;
 
-	if (len > buf->page_len)
-		len = buf-> page_len;
-
-	result = _shift_data_right_tail(buf, pglen - len, len);
-	buf->page_len -= len;
-	buf->buflen -= len;
-	/* Have we truncated the message? */
-	if (buf->len > buf->buflen)
-		buf->len = buf->buflen;
-
-	return result;
+	WARN_ON_ONCE(len > buf->page_len);
+	if (buf->head->iov_len >= buf->len || len > buflen)
+		buflen = len;
+	if (buf->page_len > buflen) {
+		buf->buflen -= buf->page_len - buflen;
+		buf->page_len = buflen;
+	}
+	if (len >= buf->page_len)
+		return 0;
+	shift = buf->page_len - len;
+	xdr_buf_try_expand(buf, shift);
+	xdr_buf_pages_shift_right(buf, len, buflen - len, shift);
+	buf->page_len = len;
+	buf->len -= shift;
+	buf->buflen -= shift;
+	return shift;
 }
 
 void
 xdr_shift_buf(struct xdr_buf *buf, size_t len)
 {
-	xdr_shrink_bufhead(buf, len);
+	xdr_shrink_bufhead(buf, buf->head->iov_len - len);
 }
 EXPORT_SYMBOL_GPL(xdr_shift_buf);
 
@@ -636,6 +852,18 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+static void xdr_stream_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	unsigned int blen = xdr->buf->len;
+
+	xdr->nwords = blen > pos ? XDR_QUADLEN(blen) - XDR_QUADLEN(pos) : 0;
+}
+
+static void xdr_stream_page_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	xdr_stream_set_pos(xdr, pos + xdr->buf->head[0].iov_len);
+}
+
 /**
  * xdr_page_pos - Return the current offset from the start of the xdr pages
  * @xdr: pointer to struct xdr_stream
@@ -969,19 +1197,31 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b
 }
 EXPORT_SYMBOL_GPL(xdr_write_pages);
 
-static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
-		unsigned int len)
+static unsigned int xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
+				unsigned int base, unsigned int len)
 {
 	if (len > iov->iov_len)
 		len = iov->iov_len;
-	xdr->p = (__be32*)iov->iov_base;
+	if (unlikely(base > len))
+		base = len;
+	xdr->p = (__be32*)(iov->iov_base + base);
 	xdr->end = (__be32*)(iov->iov_base + len);
 	xdr->iov = iov;
 	xdr->page_ptr = NULL;
+	return len - base;
+}
+
+static unsigned int xdr_set_tail_base(struct xdr_stream *xdr,
+				      unsigned int base, unsigned int len)
+{
+	struct xdr_buf *buf = xdr->buf;
+
+	xdr_stream_set_pos(xdr, base + buf->page_len + buf->head->iov_len);
+	return xdr_set_iov(xdr, buf->tail, base, len);
 }
 
-static int xdr_set_page_base(struct xdr_stream *xdr,
-		unsigned int base, unsigned int len)
+static unsigned int xdr_set_page_base(struct xdr_stream *xdr,
+				      unsigned int base, unsigned int len)
 {
 	unsigned int pgnr;
 	unsigned int maxlen;
@@ -990,12 +1230,15 @@ static int xdr_set_page_base(struct xdr_stream *xdr,
 	void *kaddr;
 
 	maxlen = xdr->buf->page_len;
-	if (base >= maxlen)
-		return -EINVAL;
-	maxlen -= base;
+	if (base >= maxlen) {
+		base = maxlen;
+		maxlen = 0;
+	} else
+		maxlen -= base;
 	if (len > maxlen)
 		len = maxlen;
 
+	xdr_stream_page_set_pos(xdr, base);
 	base += xdr->buf->page_base;
 
 	pgnr = base >> PAGE_SHIFT;
@@ -1010,14 +1253,16 @@ static int xdr_set_page_base(struct xdr_stream *xdr,
 		pgend = PAGE_SIZE;
 	xdr->end = (__be32*)(kaddr + pgend);
 	xdr->iov = NULL;
-	return 0;
+	return len;
 }
 
 static void xdr_set_page(struct xdr_stream *xdr, unsigned int base,
 			 unsigned int len)
 {
-	if (xdr_set_page_base(xdr, base, len) < 0)
-		xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
+	if (xdr_set_page_base(xdr, base, len) == 0) {
+		base -= xdr->buf->page_len;
+		xdr_set_tail_base(xdr, base, len);
+	}
 }
 
 static void xdr_set_next_page(struct xdr_stream *xdr)
@@ -1026,17 +1271,18 @@ static void xdr_set_next_page(struct xdr_stream *xdr)
 
 	newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT;
 	newbase -= xdr->buf->page_base;
-
-	xdr_set_page(xdr, newbase, PAGE_SIZE);
+	if (newbase < xdr->buf->page_len)
+		xdr_set_page_base(xdr, newbase, xdr_stream_remaining(xdr));
+	else
+		xdr_set_tail_base(xdr, 0, xdr_stream_remaining(xdr));
 }
 
 static bool xdr_set_next_buffer(struct xdr_stream *xdr)
 {
 	if (xdr->page_ptr != NULL)
 		xdr_set_next_page(xdr);
-	else if (xdr->iov == xdr->buf->head) {
-		xdr_set_page(xdr, 0, PAGE_SIZE);
-	}
+	else if (xdr->iov == xdr->buf->head)
+		xdr_set_page(xdr, 0, xdr_stream_remaining(xdr));
 	return xdr->p != xdr->end;
 }
 
@@ -1053,12 +1299,9 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 	xdr->buf = buf;
 	xdr_reset_scratch_buffer(xdr);
 	xdr->nwords = XDR_QUADLEN(buf->len);
-	if (buf->head[0].iov_len != 0)
-		xdr_set_iov(xdr, buf->head, buf->len);
-	else if (buf->page_len != 0)
-		xdr_set_page_base(xdr, 0, buf->len);
-	else
-		xdr_set_iov(xdr, buf->head, buf->len);
+	if (xdr_set_iov(xdr, buf->head, 0, buf->len) == 0 &&
+	    xdr_set_page_base(xdr, 0, buf->len) == 0)
+		xdr_set_iov(xdr, buf->tail, 0, buf->len);
 	if (p != NULL && p > xdr->p && xdr->end >= p) {
 		xdr->nwords -= p - xdr->p;
 		xdr->p = p;
@@ -1158,14 +1401,13 @@ static void xdr_realign_pages(struct xdr_stream *xdr)
 	struct xdr_buf *buf = xdr->buf;
 	struct kvec *iov = buf->head;
 	unsigned int cur = xdr_stream_pos(xdr);
-	unsigned int copied, offset;
+	unsigned int copied;
 
 	/* Realign pages to current pointer position */
 	if (iov->iov_len > cur) {
-		offset = iov->iov_len - cur;
-		copied = xdr_shrink_bufhead(buf, offset);
-		trace_rpc_xdr_alignment(xdr, offset, copied);
-		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+		copied = xdr_shrink_bufhead(buf, cur);
+		trace_rpc_xdr_alignment(xdr, cur, copied);
+		xdr_set_page(xdr, 0, buf->page_len);
 	}
 }
 
@@ -1173,8 +1415,7 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 {
 	struct xdr_buf *buf = xdr->buf;
 	unsigned int nwords = XDR_QUADLEN(len);
-	unsigned int cur = xdr_stream_pos(xdr);
-	unsigned int copied, offset;
+	unsigned int copied;
 
 	if (xdr->nwords == 0)
 		return 0;
@@ -1188,125 +1429,103 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 		len = buf->page_len;
 	else if (nwords < xdr->nwords) {
 		/* Truncate page data and move it into the tail */
-		offset = buf->page_len - len;
-		copied = xdr_shrink_pagelen(buf, offset);
-		trace_rpc_xdr_alignment(xdr, offset, copied);
-		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+		copied = xdr_shrink_pagelen(buf, len);
+		trace_rpc_xdr_alignment(xdr, len, copied);
 	}
 	return len;
 }
 
 /**
- * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position
+ * xdr_read_pages - align page-based XDR data to current pointer position
  * @xdr: pointer to xdr_stream struct
  * @len: number of bytes of page data
  *
  * Moves data beyond the current pointer position from the XDR head[] buffer
- * into the page list. Any data that lies beyond current position + "len"
- * bytes is moved into the XDR tail[].
+ * into the page list. Any data that lies beyond current position + @len
+ * bytes is moved into the XDR tail[]. The xdr_stream current position is
+ * then advanced past that data to align to the next XDR object in the tail.
  *
  * Returns the number of XDR encoded bytes now contained in the pages
  */
 unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 {
-	struct xdr_buf *buf = xdr->buf;
-	struct kvec *iov;
-	unsigned int nwords;
-	unsigned int end;
-	unsigned int padding;
+	unsigned int nwords = XDR_QUADLEN(len);
+	unsigned int base, end, pglen;