Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

4 files changed, 1585 insertions, 0 deletions

diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile
new file mode 100644
index 000000000..de056312d
--- /dev/null
+++ b/fs/nfs/filelayout/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the pNFS Files Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
new file mode 100644
index 000000000..72e20b56f
--- /dev/null
+++ b/fs/nfs/filelayout/filelayout.c
@@ -0,0 +1,1155 @@
+/*
+ *  Module for the pnfs nfs4 file layout driver.
+ *  Defines all I/O and Policy interface operations, plus code
+ *  to register itself with the pNFS client.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+
+#include <linux/sunrpc/metrics.h>
+
+#include "../nfs4session.h"
+#include "../internal.h"
+#include "../delegation.h"
+#include "filelayout.h"
+#include "../nfs4trace.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>");
+MODULE_DESCRIPTION("The NFSv4 file layout driver");
+
+#define FILELAYOUT_POLL_RETRY_MAX     (15*HZ)
+static const struct pnfs_commit_ops filelayout_commit_ops;
+
+static loff_t
+filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg,
+			    loff_t offset)
+{
+	u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count;
+	u64 stripe_no;
+	u32 rem;
+
+	offset -= flseg->pattern_offset;
+	stripe_no = div_u64(offset, stripe_width);
+	div_u64_rem(offset, flseg->stripe_unit, &rem);
+
+	return stripe_no * flseg->stripe_unit + rem;
+}
+
+/* This function is used by the layout driver to calculate the
+ * offset of the file on the dserver based on whether the
+ * layout type is STRIPE_DENSE or STRIPE_SPARSE
+ */
+static loff_t
+filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	switch (flseg->stripe_type) {
+	case STRIPE_SPARSE:
+		return offset;
+
+	case STRIPE_DENSE:
+		return filelayout_get_dense_offset(flseg, offset);
+	}
+
+	BUG();
+}
+
+static void filelayout_reset_write(struct nfs_pgio_header *hdr)
+{
+	struct rpc_task *task = &hdr->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)hdr->inode->i_ino,
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_write_done_resend_to_mds(hdr);
+	}
+}
+
+static void filelayout_reset_read(struct nfs_pgio_header *hdr)
+{
+	struct rpc_task *task = &hdr->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)hdr->inode->i_ino,
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_read_done_resend_to_mds(hdr);
+	}
+}
+
+static int filelayout_async_handle_error(struct rpc_task *task,
+					 struct nfs4_state *state,
+					 struct nfs_client *clp,
+					 struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_hdr *lo = lseg->pls_layout;
+	struct inode *inode = lo->plh_inode;
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
+	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
+
+	if (task->tk_status >= 0)
+		return 0;
+
+	switch (task->tk_status) {
+	/* DS session errors */
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_BADSLOT:
+	case -NFS4ERR_BAD_HIGH_SLOT:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+	case -NFS4ERR_SEQ_MISORDERED:
+		dprintk("%s ERROR %d, Reset session. Exchangeid "
+			"flags 0x%x\n", __func__, task->tk_status,
+			clp->cl_exchange_flags);
+		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
+		break;
+	case -NFS4ERR_DELAY:
+	case -NFS4ERR_GRACE:
+		rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX);
+		break;
+	case -NFS4ERR_RETRY_UNCACHED_REP:
+		break;
+	/* Invalidate Layout errors */
+	case -NFS4ERR_ACCESS:
+	case -NFS4ERR_PNFS_NO_LAYOUT:
+	case -ESTALE:           /* mapped NFS4ERR_STALE */
+	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
+	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
+	case -NFS4ERR_FHEXPIRED:
+	case -NFS4ERR_WRONG_TYPE:
+		dprintk("%s Invalid layout error %d\n", __func__,
+			task->tk_status);
+		/*
+		 * Destroy layout so new i/o will get a new layout.
+		 * Layout will not be destroyed until all current lseg
+		 * references are put. Mark layout as invalid to resend failed
+		 * i/o and all i/o waiting on the slot table to the MDS until
+		 * layout is destroyed and a new valid layout is obtained.
+		 */
+		pnfs_destroy_layout(NFS_I(inode));
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		goto reset;
+	/* RPC connection errors */
+	case -ECONNREFUSED:
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -EIO:
+	case -ETIMEDOUT:
+	case -EPIPE:
+	case -EPROTO:
+	case -ENODEV:
+		dprintk("%s DS connection error %d\n", __func__,
+			task->tk_status);
+		nfs4_mark_deviceid_unavailable(devid);
+		pnfs_error_mark_layout_for_return(inode, lseg);
+		pnfs_set_lo_fail(lseg);
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		fallthrough;
+	default:
+reset:
+		dprintk("%s Retry through MDS. Error %d\n", __func__,
+			task->tk_status);
+		return -NFS4ERR_RESET_TO_MDS;
+	}
+	task->tk_status = 0;
+	return -EAGAIN;
+}
+
+/* NFS_PROTO call done callback routines */
+
+static int filelayout_read_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	int err;
+
+	trace_nfs4_pnfs_read(hdr, task->tk_status);
+	err = filelayout_async_handle_error(task, hdr->args.context->state,
+					    hdr->ds_clp, hdr->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_read(hdr);
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * We reference the rpc_cred of the first WRITE that triggers the need for
+ * a LAYOUTCOMMIT, and use it to send the layoutcommit compound.
+ * rfc5661 is not clear about which credential should be used.
+ */
+static void
+filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
+{
+	loff_t end_offs = 0;
+
+	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
+	    hdr->res.verf->committed == NFS_FILE_SYNC)
+		return;
+	if (hdr->res.verf->committed == NFS_DATA_SYNC)
+		end_offs = hdr->mds_offset + (loff_t)hdr->res.count;
+
+	/* Note: if the write is unstable, don't set end_offs until commit */
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg, end_offs);
+	dprintk("%s inode %llu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
+}
+
+bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return filelayout_test_devid_invalid(node) ||
+		nfs4_test_deviceid_unavailable(node);
+}
+
+static bool
+filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_deviceid_node *node = FILELAYOUT_DEVID_NODE(lseg);
+
+	return filelayout_test_devid_unavailable(node);
+}
+
+/*
+ * Call ops for the async read/write cases
+ * In the case of dense layouts, the offset needs to be reset to its
+ * original value.
+ */
+static void filelayout_read_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return;
+	}
+	if (filelayout_reset_to_mds(hdr->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_read(hdr);
+		rpc_exit(task, 0);
+		return;
+	}
+	hdr->pgio_done_cb = filelayout_read_done_cb;
+
+	if (nfs4_setup_sequence(hdr->ds_clp,
+			&hdr->args.seq_args,
+			&hdr->res.seq_res,
+			task))
+		return;
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_READ) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void filelayout_read_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs41_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_read_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
+}
+
+static int filelayout_write_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	int err;
+
+	trace_nfs4_pnfs_write(hdr, task->tk_status);
+	err = filelayout_async_handle_error(task, hdr->args.context->state,
+					    hdr->ds_clp, hdr->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_write(hdr);
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	filelayout_set_layoutcommit(hdr);
+
+	/* zero out the fattr */
+	hdr->fattr.valid = 0;
+	if (task->tk_status >= 0)
+		nfs_writeback_update_inode(hdr);
+
+	return 0;
+}
+
+static int filelayout_commit_done_cb(struct rpc_task *task,
+				     struct nfs_commit_data *data)
+{
+	int err;
+
+	trace_nfs4_pnfs_commit_ds(data, task->tk_status);
+	err = filelayout_async_handle_error(task, NULL, data->ds_clp,
+					    data->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		pnfs_generic_prepare_to_resend_writes(data);
+		return -EAGAIN;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
+
+	return 0;
+}
+
+static void filelayout_write_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return;
+	}
+	if (filelayout_reset_to_mds(hdr->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_write(hdr);
+		rpc_exit(task, 0);
+		return;
+	}
+	if (nfs4_setup_sequence(hdr->ds_clp,
+			&hdr->args.seq_args,
+			&hdr->res.seq_res,
+			task))
+		return;
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_WRITE) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void filelayout_write_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs41_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_write_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
+}
+
+static void filelayout_commit_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	nfs4_setup_sequence(wdata->ds_clp,
+			&wdata->args.seq_args,
+			&wdata->res.seq_res,
+			task);
+}
+
+static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *cdata = data;
+
+	rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
+}
+
+static const struct rpc_call_ops filelayout_read_call_ops = {
+	.rpc_call_prepare = filelayout_read_prepare,
+	.rpc_call_done = filelayout_read_call_done,
+	.rpc_count_stats = filelayout_read_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops filelayout_write_call_ops = {
+	.rpc_call_prepare = filelayout_write_prepare,
+	.rpc_call_done = filelayout_write_call_done,
+	.rpc_count_stats = filelayout_write_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops filelayout_commit_call_ops = {
+	.rpc_call_prepare = filelayout_commit_prepare,
+	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_count_stats = filelayout_commit_count_stats,
+	.rpc_release = pnfs_generic_commit_release,
+};
+
+static enum pnfs_try_status
+filelayout_read_pagelist(struct nfs_pgio_header *hdr)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	loff_t offset = hdr->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+
+	dprintk("--> %s ino %llu pgbase %u req %zu@%llu\n",
+		__func__, hdr->inode->i_ino,
+		hdr->args.pgbase, (size_t)hdr->args.count, offset);
+
+	/* Retrieve the correct rpc_client for the byte range */
+	j = nfs4_fl_calc_j_index(lseg, offset);
+	idx = nfs4_fl_calc_ds_index(lseg, j);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
+	dprintk("%s USE DS: %s cl_count %d\n", __func__,
+		ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
+
+	/* No multipath support. Use first DS */
+	refcount_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	hdr->ds_commit_idx = idx;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		hdr->args.fh = fh;
+
+	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
+	hdr->mds_offset = offset;
+
+	/* Perform an asynchronous read to ds */
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
+			  0, RPC_TASK_SOFTCONN, NULL);
+	return PNFS_ATTEMPTED;
+}
+
+/* Perform async writes. */
+static enum pnfs_try_status
+filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	loff_t offset = hdr->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+
+	/* Retrieve the correct rpc_client for the byte range */
+	j = nfs4_fl_calc_j_index(lseg, offset);
+	idx = nfs4_fl_calc_ds_index(lseg, j);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
+	dprintk("%s ino %llu sync %d req %zu@%llu DS: %s cl_count %d\n",
+		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
+		offset, ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
+
+	hdr->pgio_done_cb = filelayout_write_done_cb;
+	refcount_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	hdr->ds_commit_idx = idx;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		hdr->args.fh = fh;
+	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
+
+	/* Perform an asynchronous write */
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
+			  sync, RPC_TASK_SOFTCONN, NULL);
+	return PNFS_ATTEMPTED;
+}
+
+static int
+filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
+			  struct nfs4_filelayout_segment *fl,
+			  gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *dsaddr;
+	int status = -EINVAL;
+
+	/* Is the deviceid already set? If so, we're good. */
+	if (fl->dsaddr != NULL)
+		return 0;
+
+	/* find and reference the deviceid */
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
+			lo->plh_lc_cred, gfp_flags);
+	if (d == NULL)
+		goto out;
+
+	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
+		goto out_put;
+
+	if (fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %u\n",
+				__func__, fl->first_stripe_index);
+		goto out_put;
+	}
+
+	if ((fl->stripe_type == STRIPE_SPARSE &&
+	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
+	    (fl->stripe_type == STRIPE_DENSE &&
+	    fl->num_fh != dsaddr->stripe_count)) {
+		dprintk("%s num_fh %u not valid for given packing\n",
+			__func__, fl->num_fh);
+		goto out_put;
+	}
+	status = 0;
+
+	/*
+	 * Atomic compare and xchange to ensure we don't scribble
+	 * over a non-NULL pointer.
+	 */
+	if (cmpxchg(&fl->dsaddr, NULL, dsaddr) != NULL)
+		goto out_put;
+out:
+	return status;
+out_put:
+	nfs4_fl_put_deviceid(dsaddr);
+	goto out;
+}
+
+/*
+ * filelayout_check_layout()
+ *
+ * Make sure layout segment parameters are sane WRT the device.
+ * At this point no generic layer initialization of the lseg has occurred,
+ * and nothing has been added to the layout_hdr cache.
+ *
+ */
+static int
+filelayout_check_layout(struct pnfs_layout_hdr *lo,
+			struct nfs4_filelayout_segment *fl,
+			struct nfs4_layoutget_res *lgr,
+			gfp_t gfp_flags)
+{
+	int status = -EINVAL;
+
+	dprintk("--> %s\n", __func__);
+
+	if (fl->pattern_offset > lgr->range.offset) {
+		dprintk("%s pattern_offset %lld too large\n",
+				__func__, fl->pattern_offset);
+		goto out;
+	}
+
+	if (!fl->stripe_unit) {
+		dprintk("%s Invalid stripe unit (%u)\n",
+			__func__, fl->stripe_unit);
+		goto out;
+	}
+
+	status = 0;
+out:
+	dprintk("--> %s returns %d\n", __func__, status);
+	return status;
+}
+
+static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
+{
+	int i;
+
+	if (fl->fh_array) {
+		for (i = 0; i < fl->num_fh; i++) {
+			if (!fl->fh_array[i])
+				break;
+			kfree(fl->fh_array[i]);
+		}
+		kfree(fl->fh_array);
+	}
+	kfree(fl);
+}
+
+static int
+filelayout_decode_layout(struct pnfs_layout_hdr *flo,
+			 struct nfs4_filelayout_segment *fl,
+			 struct nfs4_layoutget_res *lgr,
+			 gfp_t gfp_flags)
+{
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct folio *scratch;
+	__be32 *p;
+	uint32_t nfl_util;
+	int i;
+
+	dprintk("%s: set_layout_map Begin\n", __func__);
+
+	scratch = folio_alloc(gfp_flags, 0);
+	if (!scratch)
+		return -ENOMEM;
+
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
+	xdr_set_scratch_folio(&stream, scratch);
+
+	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
+	 * num_fh (4) */
+	p = xdr_inline_decode(&stream, NFS4_DEVICEID4_SIZE + 20);
+	if (unlikely(!p))
+		goto out_err;
+
+	memcpy(&fl->deviceid, p, sizeof(fl->deviceid));
+	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+	nfs4_print_deviceid(&fl->deviceid);
+
+	nfl_util = be32_to_cpup(p++);
+	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
+		fl->commit_through_mds = 1;
+	if (nfl_util & NFL4_UFLG_DENSE)
+		fl->stripe_type = STRIPE_DENSE;
+	else
+		fl->stripe_type = STRIPE_SPARSE;
+	fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK;
+
+	fl->first_stripe_index = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &fl->pattern_offset);
+	fl->num_fh = be32_to_cpup(p++);
+
+	dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n",
+		__func__, nfl_util, fl->num_fh, fl->first_stripe_index,
+		fl->pattern_offset);
+
+	/* Note that a zero value for num_fh is legal for STRIPE_SPARSE.
+	 * Futher checking is done in filelayout_check_layout */
+	if (fl->num_fh >
+	    max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT))
+		goto out_err;
+
+	if (fl->num_fh > 0) {
+		fl->fh_array = kzalloc_objs(fl->fh_array[0], fl->num_fh,
+					    gfp_flags);
+		if (!fl->fh_array)
+			goto out_err;
+	}
+
+	for (i = 0; i < fl->num_fh; i++) {
+		/* Do we want to use a mempool here? */
+		fl->fh_array[i] = kmalloc_obj(struct nfs_fh, gfp_flags);
+		if (!fl->fh_array[i])
+			goto out_err;
+
+		p = xdr_inline_decode(&stream, 4);
+		if (unlikely(!p))
+			goto out_err;
+		fl->fh_array[i]->size = be32_to_cpup(p++);
+		if (fl->fh_array[i]->size > NFS_MAXFHSIZE) {
+			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
+			       i, fl->fh_array[i]->size);
+			goto out_err;
+		}
+
+		p = xdr_inline_decode(&stream, fl->fh_array[i]->size);
+		if (unlikely(!p))
+			goto out_err;
+		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
+		dprintk("DEBUG: %s: fh len %d\n", __func__,
+			fl->fh_array[i]->size);
+	}
+
+	folio_put(scratch);
+	return 0;
+
+out_err:
+	folio_put(scratch);
+	return -EIO;
+}
+
+static void
+filelayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+
+	dprintk("--> %s\n", __func__);
+	if (fl->dsaddr != NULL)
+		nfs4_fl_put_deviceid(fl->dsaddr);
+	/* This assumes a single RW lseg */
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		struct nfs4_filelayout *flo;
+		struct inode *inode;
+
+		flo = FILELAYOUT_FROM_HDR(lseg->pls_layout);
+		inode = flo->generic_hdr.plh_inode;
+		spin_lock(&inode->i_lock);
+		pnfs_generic_ds_cinfo_release_lseg(&flo->commit_info, lseg);
+		spin_unlock(&inode->i_lock);
+	}
+	_filelayout_free_lseg(fl);
+}
+
+static struct pnfs_layout_segment *
+filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
+		      struct nfs4_layoutget_res *lgr,
+		      gfp_t gfp_flags)
+{
+	struct nfs4_filelayout_segment *fl;
+	int rc;
+
+	dprintk("--> %s\n", __func__);
+	fl = kzalloc_obj(*fl, gfp_flags);
+	if (!fl)
+		return NULL;
+
+	rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags);
+	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) {
+		_filelayout_free_lseg(fl);
+		return NULL;
+	}
+	return &fl->generic_hdr;
+}
+
+static bool
+filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
+{
+	if (flseg->dsaddr)
+		return flseg->dsaddr->stripe_count > 1;
+	return flseg->num_fh > 1;
+}
+
+/*
+ * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
+ *
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
+filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		   struct nfs_page *req)
+{
+	unsigned int size;
+	u64 p_stripe, r_stripe;
+	u32 stripe_offset;
+	u64 segment_offset = pgio->pg_lseg->pls_range.offset;
+	u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
+
+	/* calls nfs_generic_pg_test */
+	size = pnfs_generic_pg_test(pgio, prev, req);
+	if (!size)
+		return 0;
+	else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg)))
+		return size;
+
+	/* see if req and prev are in the same stripe */
+	if (prev) {
+		p_stripe = (u64)req_offset(prev) - segment_offset;
+		r_stripe = (u64)req_offset(req) - segment_offset;
+		do_div(p_stripe, stripe_unit);
+		do_div(r_stripe, stripe_unit);
+
+		if (p_stripe != r_stripe)
+			return 0;
+	}
+
+	/* calculate remaining bytes in the current stripe */
+	div_u64_rem((u64)req_offset(req) - segment_offset,
+			stripe_unit,
+			&stripe_offset);
+	WARN_ON_ONCE(stripe_offset > stripe_unit);
+	if (stripe_offset >= stripe_unit)
+		return 0;
+	return min(stripe_unit - (unsigned int)stripe_offset, size);
+}
+
+static struct pnfs_layout_segment *
+fl_pnfs_update_layout(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      loff_t pos,
+		      u64 count,
+		      enum pnfs_iomode iomode,
+		      bool strict_iomode,
+		      gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *lseg = NULL;
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_filelayout_segment *fl;
+	int status;
+
+	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
+				  gfp_flags);
+	if (IS_ERR(lseg)) {
+		/* Fall back to MDS on recoverable errors */
+		if (!nfs_error_is_fatal_on_server(PTR_ERR(lseg)))
+			lseg = NULL;
+		goto out;
+	} else if (!lseg)
+		goto out;
+
+	lo = NFS_I(ino)->layout;
+	fl = FILELAYOUT_LSEG(lseg);
+
+	status = filelayout_check_deviceid(lo, fl, gfp_flags);
+	if (status) {
+		pnfs_error_mark_layout_for_return(ino, lseg);
+		pnfs_set_lo_fail(lseg);
+		pnfs_put_lseg(lseg);
+		lseg = NULL;
+	}
+out:
+	return lseg;
+}
+
+static void
+filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	pnfs_generic_pg_check_layout(pgio, req);
+	if (!pgio->pg_lseg) {
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      nfs_req_openctx(req),
+						      req_offset(req),
+						      req->wb_bytes,
+						      IOMODE_READ,
+						      false,
+						      nfs_io_gfp_mask());
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+	/* If no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_read_mds(pgio);
+}
+
+static void
+filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			 struct nfs_page *req)
+{
+	pnfs_generic_pg_check_layout(pgio, req);
+	if (!pgio->pg_lseg) {
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      nfs_req_openctx(req),
+						      req_offset(req),
+						      req->wb_bytes,
+						      IOMODE_RW,
+						      false,
+						      nfs_io_gfp_mask());
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+
+	/* If no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_write_mds(pgio);
+}
+
+static const struct nfs_pageio_ops filelayout_pg_read_ops = {
+	.pg_init = filelayout_pg_init_read,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static const struct nfs_pageio_ops filelayout_pg_write_ops = {
+	.pg_init = filelayout_pg_init_write,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
+{
+	if (fl->stripe_type == STRIPE_SPARSE)
+		return nfs4_fl_calc_ds_index(&fl->generic_hdr, j);
+	else
+		return j;
+}
+
+static void
+filelayout_mark_request_commit(struct nfs_page *req,
+			       struct pnfs_layout_segment *lseg,
+			       struct nfs_commit_info *cinfo,
+			       u32 ds_commit_idx)
+
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+	u32 i, j;
+
+	if (fl->commit_through_mds) {
+		nfs_request_add_commit_list(req, cinfo);
+	} else {
+		/* Note that we are calling nfs4_fl_calc_j_index on each page
+		 * that ends up being committed to a data server.  An attractive
+		 * alternative is to add a field to nfs_write_data and nfs_page
+		 * to store the value calculated in filelayout_write_pagelist
+		 * and just use that here.
+		 */
+		j = nfs4_fl_calc_j_index(lseg, req_offset(req));
+		i = select_bucket_index(fl, j);
+		pnfs_layout_mark_request_commit(req, lseg, cinfo, i);
+	}
+}
+
+static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	if (flseg->stripe_type == STRIPE_SPARSE)
+		return i;
+	else
+		return nfs4_fl_calc_ds_index(lseg, i);
+}
+
+static struct nfs_fh *
+select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	if (flseg->stripe_type == STRIPE_SPARSE) {
+		if (flseg->num_fh == 1)
+			i = 0;
+		else if (flseg->num_fh == 0)
+			/* Use the MDS OPEN fh set in nfs_read_rpcsetup */
+			return NULL;
+	}
+	return flseg->fh_array[i];
+}
+
+static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
+{
+	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	u32 idx;
+	struct nfs_fh *fh;
+
+	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		goto out_err;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, data->inode);
+	if (IS_ERR(ds_clnt))
+		goto out_err;
+
+	dprintk("%s ino %llu, how %d cl_count %d\n", __func__,
+		data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count));
+	data->commit_done_cb = filelayout_commit_done_cb;
+	refcount_inc(&ds->ds_clp->cl_count);
+	data->ds_clp = ds->ds_clp;
+	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
+	if (fh)
+		data->args.fh = fh;
+	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
+				   &filelayout_commit_call_ops, how,
+				   RPC_TASK_SOFTCONN, NULL);
+out_err:
+	pnfs_generic_prepare_to_resend_writes(data);
+	pnfs_generic_commit_release(data);
+	return -EAGAIN;
+}
+
+static int
+filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
+			   int how, struct nfs_commit_info *cinfo)
+{
+	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
+					    filelayout_initiate_commit);
+}
+
+static struct nfs4_deviceid_node *
+filelayout_alloc_deviceid_node(struct nfs_server *server,
+		struct pnfs_device *pdev, gfp_t gfp_flags)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr;
+
+	dsaddr = nfs4_fl_alloc_deviceid_node(server, pdev, gfp_flags);
+	if (!dsaddr)
+		return NULL;
+	return &dsaddr->id_node;
+}
+
+static void
+filelayout_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
+}
+
+static struct pnfs_layout_hdr *
+filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+	struct nfs4_filelayout *flo;
+
+	flo = kzalloc_obj(*flo, gfp_flags);
+	if (flo == NULL)
+		return NULL;
+	pnfs_init_ds_commit_info(&flo->commit_info);
+	flo->commit_info.ops = &filelayout_commit_ops;
+	return &flo->generic_hdr;
+}
+
+static void
+filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	kfree_rcu(FILELAYOUT_FROM_HDR(lo), generic_hdr.plh_rcu);
+}
+
+static struct pnfs_ds_commit_info *
+filelayout_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;
+
+	if (layout == NULL)
+		return NULL;
+	else
+		return &FILELAYOUT_FROM_HDR(layout)->commit_info;
+}
+
+static void
+filelayout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo,
+		struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct pnfs_commit_array *array, *new;
+	unsigned int size = (fl->stripe_type == STRIPE_SPARSE) ?
+		fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
+
+	new = pnfs_alloc_commit_array(size, nfs_io_gfp_mask());
+	if (new) {
+		spin_lock(&inode->i_lock);
+		array = pnfs_add_commit_array(fl_cinfo, new, lseg);
+		spin_unlock(&inode->i_lock);
+		if (array != new)
+			pnfs_free_commit_array(new);
+	}
+}
+
+static void
+filelayout_release_ds_info(struct pnfs_ds_commit_info *fl_cinfo,
+		struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	pnfs_generic_ds_cinfo_destroy(fl_cinfo);
+	spin_unlock(&inode->i_lock);
+}
+
+static const struct pnfs_commit_ops filelayout_commit_ops = {
+	.setup_ds_info		= filelayout_setup_ds_info,
+	.release_ds_info	= filelayout_release_ds_info,
+	.mark_request_commit	= filelayout_mark_request_commit,
+	.clear_request_commit	= pnfs_generic_clear_request_commit,
+	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
+	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
+	.commit_pagelist	= filelayout_commit_pagelist,
+};
+
+static struct pnfs_layoutdriver_type filelayout_type = {
+	.id			= LAYOUT_NFSV4_1_FILES,
+	.name			= "LAYOUT_NFSV4_1_FILES",
+	.owner			= THIS_MODULE,
+	.flags			= PNFS_LAYOUTGET_ON_OPEN,
+	.max_layoutget_response	= 4096, /* 1 page or so... */
+	.alloc_layout_hdr	= filelayout_alloc_layout_hdr,
+	.free_layout_hdr	= filelayout_free_layout_hdr,
+	.alloc_lseg		= filelayout_alloc_lseg,
+	.free_lseg		= filelayout_free_lseg,
+	.pg_read_ops		= &filelayout_pg_read_ops,
+	.pg_write_ops		= &filelayout_pg_write_ops,
+	.get_ds_info		= &filelayout_get_ds_info,
+	.read_pagelist		= filelayout_read_pagelist,
+	.write_pagelist		= filelayout_write_pagelist,
+	.alloc_deviceid_node	= filelayout_alloc_deviceid_node,
+	.free_deviceid_node	= filelayout_free_deviceid_node,
+	.sync			= pnfs_nfs_generic_sync,
+};
+
+static int __init nfs4filelayout_init(void)
+{
+	printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n",
+	       __func__);
+	return pnfs_register_layoutdriver(&filelayout_type);
+}
+
+static void __exit nfs4filelayout_exit(void)
+{
+	printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n",
+	       __func__);
+	pnfs_unregister_layoutdriver(&filelayout_type);
+}
+
+MODULE_ALIAS("nfs-layouttype4-1");
+
+module_init(nfs4filelayout_init);
+module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
new file mode 100644
index 000000000..c7bb5da93
--- /dev/null
+++ b/fs/nfs/filelayout/filelayout.h
@@ -0,0 +1,118 @@
+/*
+ *  NFSv4 file layout driver data structures.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#ifndef FS_NFS_NFS4FILELAYOUT_H
+#define FS_NFS_NFS4FILELAYOUT_H
+
+#include "../pnfs.h"
+
+/*
+ * Field testing shows we need to support up to 4096 stripe indices.
+ * We store each index as a u8 (u32 on the wire) to keep the memory footprint
+ * reasonable. This in turn means we support a maximum of 256
+ * RFC 5661 multipath_list4 structures.
+ */
+#define NFS4_PNFS_MAX_STRIPE_CNT 4096
+#define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
+
+enum stripetype4 {
+	STRIPE_SPARSE = 1,
+	STRIPE_DENSE = 2
+};
+
+struct nfs4_file_layout_dsaddr {
+	struct nfs4_deviceid_node	id_node;
+	u32				stripe_count;
+	u8				*stripe_indices;
+	u32				ds_num;
+	struct nfs4_pnfs_ds		*ds_list[] __counted_by(ds_num);
+};
+
+struct nfs4_filelayout_segment {
+	struct pnfs_layout_segment	generic_hdr;
+	u32				stripe_type;
+	u32				commit_through_mds;
+	u32				stripe_unit;
+	u32				first_stripe_index;
+	u64				pattern_offset;
+	struct nfs4_deviceid		deviceid;
+	struct nfs4_file_layout_dsaddr	*dsaddr; /* Point to GETDEVINFO data */
+	unsigned int			num_fh;
+	struct nfs_fh			**fh_array;
+};
+
+struct nfs4_filelayout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+};
+
+static inline struct nfs4_filelayout *
+FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_filelayout, generic_hdr);
+}
+
+static inline struct nfs4_filelayout_segment *
+FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_filelayout_segment,
+			    generic_hdr);
+}
+
+static inline struct nfs4_deviceid_node *
+FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
+{
+	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
+}
+
+static inline bool
+filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	return test_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
+extern bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
+
+extern struct nfs_fh *
+nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
+
+u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
+u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
+struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
+					u32 ds_idx);
+
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server,
+	struct pnfs_device *pdev, gfp_t gfp_flags);
+extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+
+#endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
new file mode 100644
index 000000000..88bc79ec3
--- /dev/null
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -0,0 +1,306 @@
+/*
+ *  Device operations for the pnfs nfs4 file layout driver.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *  Garth Goodson   <Garth.Goodson@netapp.com>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "filelayout.h"
+#include "../nfs4trace.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
+static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+
+void
+nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	struct nfs4_pnfs_ds *ds;
+	int i;
+
+	nfs4_print_deviceid(&dsaddr->id_node.deviceid);
+
+	for (i = 0; i < dsaddr->ds_num; i++) {
+		ds = dsaddr->ds_list[i];
+		if (ds != NULL)
+			nfs4_pnfs_ds_put(ds);
+	}
+	kfree(dsaddr->stripe_indices);
+	kfree_rcu(dsaddr, id_node.rcu);
+}
+
+/* Decode opaque device data and return the result */
+struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+		gfp_t gfp_flags)
+{
+	int i;
+	u32 cnt, num;
+	u8 *indexp;
+	__be32 *p;
+	u8 *stripe_indices;
+	u8 max_stripe_index;
+	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct folio *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
+	struct net *net = server->nfs_client->cl_net;
+
+	/* set up xdr stream */
+	scratch = folio_alloc(gfp_flags, 0);
+	if (!scratch)
+		goto out_err;
+
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
+	xdr_set_scratch_folio(&stream, scratch);
+
+	/* Get the stripe count (number of stripe index) */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_free_scratch;
+
+	cnt = be32_to_cpup(p);
+	dprintk("%s stripe count  %d\n", __func__, cnt);
+	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
+		printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
+		       "supported maximum %d\n", __func__,
+			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
+		goto out_err_free_scratch;
+	}
+
+	/* read stripe indices */
+	stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags);
+	if (!stripe_indices)
+		goto out_err_free_scratch;
+
+	p = xdr_inline_decode(&stream, cnt << 2);
+	if (unlikely(!p))
+		goto out_err_free_stripe_indices;
+
+	indexp = &stripe_indices[0];
+	max_stripe_index = 0;
+	for (i = 0; i < cnt; i++) {
+		*indexp = be32_to_cpup(p++);
+		max_stripe_index = max(max_stripe_index, *indexp);
+		indexp++;
+	}
+
+	/* Check the multipath list count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_free_stripe_indices;
+
+	num = be32_to_cpup(p);
+	dprintk("%s ds_num %u\n", __func__, num);
+	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
+		printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
+			"supported maximum %d\n", __func__,
+			num, NFS4_PNFS_MAX_MULTI_CNT);
+		goto out_err_free_stripe_indices;
+	}
+
+	/* validate stripe indices are all < num */
+	if (max_stripe_index >= num) {
+		printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
+			__func__, max_stripe_index, num);
+		goto out_err_free_stripe_indices;
+	}
+
+	dsaddr = kzalloc_flex(*dsaddr, ds_list, num, gfp_flags);
+	if (!dsaddr)
+		goto out_err_free_stripe_indices;
+
+	dsaddr->stripe_count = cnt;
+	dsaddr->stripe_indices = stripe_indices;
+	stripe_indices = NULL;
+	dsaddr->ds_num = num;
+	nfs4_init_deviceid_node(&dsaddr->id_node, server, &pdev->dev_id);
+
+	INIT_LIST_HEAD(&dsaddrs);
+
+	for (i = 0; i < dsaddr->ds_num; i++) {
+		int j;
+		u32 mp_count;
+
+		p = xdr_inline_decode(&stream, 4);
+		if (unlikely(!p))
+			goto out_err_free_deviceid;
+
+		mp_count = be32_to_cpup(p); /* multipath count */
+		for (j = 0; j < mp_count; j++) {
+			da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
+			if (da)
+				list_add_tail(&da->da_node, &dsaddrs);
+		}
+		if (list_empty(&dsaddrs)) {
+			dprintk("%s: no suitable DS addresses found\n",
+				__func__);
+			goto out_err_free_deviceid;
+		}
+
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, 4,
+						      gfp_flags);
+		if (!dsaddr->ds_list[i])
+			goto out_err_drain_dsaddrs;
+		trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);
+
+		/* If DS was already in cache, free ds addrs */
+		while (!list_empty(&dsaddrs)) {
+			da = list_first_entry(&dsaddrs,
+					      struct nfs4_pnfs_ds_addr,
+					      da_node);
+			list_del_init(&da->da_node);
+			kfree(da->da_remotestr);
+			kfree(da);
+		}
+	}
+
+	folio_put(scratch);
+	return dsaddr;
+
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+out_err_free_deviceid:
+	nfs4_fl_free_deviceid(dsaddr);
+	/* stripe_indicies was part of dsaddr */
+	goto out_err_free_scratch;
+out_err_free_stripe_indices:
+	kfree(stripe_indices);
+out_err_free_scratch:
+	folio_put(scratch);
+out_err:
+	dprintk("%s ERROR: returning NULL\n", __func__);
+	return NULL;
+}
+
+void
+nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	nfs4_put_deviceid_node(&dsaddr->id_node);
+}
+
+/*
+ * Want res = (offset - layout->pattern_offset)/ layout->stripe_unit
+ * Then: ((res + fsi) % dsaddr->stripe_count)
+ */
+u32
+nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+	u64 tmp;
+
+	tmp = offset - flseg->pattern_offset;
+	do_div(tmp, flseg->stripe_unit);
+	tmp += flseg->first_stripe_index;
+	return do_div(tmp, flseg->dsaddr->stripe_count);
+}
+
+u32
+nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j)
+{
+	return FILELAYOUT_LSEG(lseg)->dsaddr->stripe_indices[j];
+}
+
+struct nfs_fh *
+nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+	u32 i;
+
+	if (flseg->stripe_type == STRIPE_SPARSE) {
+		if (flseg->num_fh == 1)
+			i = 0;
+		else if (flseg->num_fh == 0)
+			/* Use the MDS OPEN fh set in nfs_read_rpcsetup */
+			return NULL;
+		else
+			i = nfs4_fl_calc_ds_index(lseg, j);
+	} else
+		i = j;
+	return flseg->fh_array[i];
+}
+
+/* Upon return, either ds is connected, or ds is NULL */
+struct nfs4_pnfs_ds *
+nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
+	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
+	struct nfs4_pnfs_ds *ret = ds;
+	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+	int status;
+
+	if (ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
+			__func__, ds_idx);
+		pnfs_generic_mark_devid_invalid(devid);
+		goto out;
+	}
+	smp_rmb();
+	if (ds->ds_clp)
+		goto out_test_devid;
+
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans, 4,
+			     s->nfs_client->cl_minorversion, true);
+	if (status) {
+		nfs4_mark_deviceid_unavailable(devid);
+		ret = NULL;
+		goto out;
+	}
+
+out_test_devid:
+	if (ret->ds_clp == NULL ||
+	    filelayout_test_devid_unavailable(devid))
+		ret = NULL;
+out:
+	return ret;
+}
+
+module_param(dataserver_retrans, uint, 0644);
+MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
+			"retries a request before it attempts further "
+			" recovery  action.");
+module_param(dataserver_timeo, uint, 0644);
+MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
+			"NFSv4.1  client  waits for a response from a "
+			" data server before it retries an NFS request.");