Re: [PATCH 13/13] RFC: pnfs: filelayout: add driver's LAYOUTGET and GETDEVICEINFO infrastructure

[Trond Myklebust <Trond.Myklebust@netapp.com>]

On Thu, 2010-09-02 at 14:00 -0400, Fred Isaman wrote:
> From: The pNFS Team <linux-nfs@vger.kernel.org>
> 
> Implement the driver's io_ops->alloc_lseg and free_lseg functions,
> which integrate into the deviceid cache and calls out to
> nfs4_proc_getdeviceinfo when necessary.
> 
> Signed-off-by: TBD - melding/reorganization of several patches
> ---
>  fs/nfs/Makefile            |    2 +-
>  fs/nfs/client.c            |    1 +
>  fs/nfs/nfs4filelayout.c    |  203 ++++++++++++++++++++-
>  fs/nfs/nfs4filelayout.h    |   74 +++++++
>  fs/nfs/nfs4filelayoutdev.c |  450 ++++++++++++++++++++++++++++++++++++++++++++
>  5 files changed, 728 insertions(+), 2 deletions(-)
>  create mode 100644 fs/nfs/nfs4filelayout.h
>  create mode 100644 fs/nfs/nfs4filelayoutdev.c
> 
> diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
> index 08a8889..4776ff9 100644
> --- a/fs/nfs/Makefile
> +++ b/fs/nfs/Makefile
> @@ -20,4 +20,4 @@ nfs-$(CONFIG_SYSCTL) += sysctl.o
>  nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
>  
>  obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
> -nfs_layout_nfsv41_files-y := nfs4filelayout.o
> +nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
> diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> index 6fc5c84..bac8ac2 100644
> --- a/fs/nfs/client.c
> +++ b/fs/nfs/client.c
> @@ -255,6 +255,7 @@ void nfs_put_client(struct nfs_client *clp)
>  		nfs_free_client(clp);
>  	}
>  }
> +EXPORT_SYMBOL(nfs_put_client);
>  
>  #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
>  /*
> diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
> index c685196..0104d09 100644
> --- a/fs/nfs/nfs4filelayout.c
> +++ b/fs/nfs/nfs4filelayout.c
> @@ -30,7 +30,9 @@
>   */
>  
>  #include <linux/nfs_fs.h>
> -#include "pnfs.h"
> +
> +#include "internal.h"
> +#include "nfs4filelayout.h"
>  
>  #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
>  
> @@ -41,18 +43,217 @@ MODULE_DESCRIPTION("The NFSv4 file layout driver");
>  int
>  filelayout_initialize_mountpoint(struct nfs_client *clp)
>  {
> +	int status = nfs4_alloc_init_deviceid_cache(clp,
> +						nfs4_fl_free_deviceid_callback);
> +	if (status) {
> +		printk(KERN_WARNING "%s: deviceid cache could not be "
> +			"initialized\n", __func__);
> +		return status;
> +	}
> +	dprintk("%s: deviceid cache has been initialized successfully\n",
> +		__func__);
>  	return 0;
>  }
>  
> +/* Uninitialize a mountpoint by destroying its device list */
>  int
>  filelayout_uninitialize_mountpoint(struct nfs_client *clp)
>  {
>  	dprintk("--> %s\n", __func__);
>  
> +	if (clp->cl_devid_cache)
> +		nfs4_put_deviceid_cache(clp);
> +	return 0;
> +}
> +
> +/*
> + * 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)
> +{
> +	struct pnfs_layout_segment *lseg = &fl->generic_hdr;
> +	struct nfs4_file_layout_dsaddr *dsaddr;
> +	int status = -EINVAL;
> +	struct nfs_server *nfss = PNFS_NFS_SERVER(lo);
> +
> +	dprintk("--> %s\n", __func__);
> +
> +	if (fl->pattern_offset > lgr->range.offset) {
> +		dprintk("%s pattern_offset %lld to large\n",
> +				__func__, fl->pattern_offset);
> +		goto out;
> +	}
> +
> +	if (fl->stripe_unit % PAGE_SIZE) {
> +		dprintk("%s Stripe unit (%u) not page aligned\n",
> +			__func__, fl->stripe_unit);
> +		goto out;
> +	}
> +
> +	/* find and reference the deviceid */
> +	dsaddr = nfs4_fl_find_get_deviceid(nfss->nfs_client, &fl->dev_id);
> +	if (dsaddr == NULL) {
> +		dsaddr = get_device_info(lo->inode, &fl->dev_id);
> +		if (dsaddr == NULL)
> +			goto out;
> +	}
> +
> +	nfs4_set_layout_deviceid(lseg, &dsaddr->deviceid);
> +
> +	if (fl->first_stripe_index < 0 ||
> +	    fl->first_stripe_index >= dsaddr->stripe_count) {
> +		dprintk("%s Bad first_stripe_index %d\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;
> +	}
> +
> +	if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
> +		dprintk("%s Stripe unit (%u) not aligned with rsize %u "
> +			"wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
> +			nfss->wsize);
> +	}
> +
> +	status = 0;
> +out:
> +	dprintk("--> %s returns %d\n", __func__, status);
> +	return status;
> +out_put:
> +	nfs4_put_layout_deviceid(lseg);
> +	goto out;
> +}
> +
> +static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl);
> +static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl);
> +
> +static int
> +filelayout_decode_layout(struct pnfs_layout_hdr *flo,
> +		      struct nfs4_filelayout_segment *fl,
> +		      struct nfs4_layoutget_res *lgr)
> +{
> +	uint32_t *p = (uint32_t *)lgr->layout.buf;
> +	uint32_t nfl_util;
> +	int i;
> +
> +	dprintk("%s: set_layout_map Begin\n", __func__);
> +
> +	memcpy(&fl->dev_id, p, sizeof(fl->dev_id));
> +	p += XDR_QUADLEN(NFS4_PNFS_DEVICEID4_SIZE);
> +	print_deviceid(&fl->dev_id);
> +
> +	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);
> +
> +	if (fl->num_fh * sizeof(struct nfs_fh) > 2*PAGE_SIZE) {
> +		fl->fh_array = vmalloc(fl->num_fh * sizeof(struct nfs_fh));
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Please do this differently. vmalloc() use is frowned upon unless you
really need _contiguous_ memory. The 32-bit vmalloc address space is
limited, and easily exhausted.

In this case you could instead allocate an array of pointers to struct
nfs_fh.

> +		if (fl->fh_array)
> +			memset(fl->fh_array, 0,
> +				fl->num_fh * sizeof(struct nfs_fh));
> +	} else {
> +		fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh),
> +					GFP_KERNEL);
> +	}
> +	if (!fl->fh_array)
> +		return -ENOMEM;
> +
> +	for (i = 0; i < fl->num_fh; i++) {
> +		/* fh */
> +		fl->fh_array[i].size = be32_to_cpup(p++);
> +		if (sizeof(struct nfs_fh) < fl->fh_array[i].size) {
> +			printk(KERN_ERR "Too big fh %d received %d\n",
> +				i, fl->fh_array[i].size);
> +			/* Layout is now invalid, pretend it doesn't exist */
> +			filelayout_free_fh_array(fl);
> +			fl->num_fh = 0;
> +			break;
> +		}
> +		memcpy(fl->fh_array[i].data, p, fl->fh_array[i].size);
> +		p += XDR_QUADLEN(fl->fh_array[i].size);
> +		dprintk("DEBUG: %s: fh len %d\n", __func__,
> +					fl->fh_array[i].size);
> +	}
> +
>  	return 0;
>  }
>  
> +static struct pnfs_layout_segment *
> +filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
> +		      struct nfs4_layoutget_res *lgr)
> +{
> +	struct nfs4_filelayout_segment *fl;
> +	int rc;
> +
> +	dprintk("--> %s\n", __func__);
> +	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
> +	if (!fl)
> +		return NULL;
> +
> +	rc = filelayout_decode_layout(layoutid, fl, lgr);
> +	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr)) {
> +		_filelayout_free_lseg(fl);
> +		return NULL;
> +	}
> +	return &fl->generic_hdr;
> +}
> +
> +static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
> +{
> +	if (fl->num_fh * sizeof(struct nfs_fh) > 2*PAGE_SIZE)
> +		vfree(fl->fh_array);

See above.

> +	else
> +		kfree(fl->fh_array);
> +
> +	fl->fh_array = NULL;
> +}
> +
> +static void
> +_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
> +{
> +	filelayout_free_fh_array(fl);
> +	kfree(fl);
> +}
> +
> +static void
> +filelayout_free_lseg(struct pnfs_layout_segment *lseg)
> +{
> +	dprintk("--> %s\n", __func__);
> +	nfs4_put_layout_deviceid(lseg);
> +	_filelayout_free_lseg(FILELAYOUT_LSEG(lseg));
> +}
> +
>  struct layoutdriver_io_operations filelayout_io_operations = {
> +	.alloc_lseg              = filelayout_alloc_lseg,
> +	.free_lseg               = filelayout_free_lseg,
>  	.initialize_mountpoint   = filelayout_initialize_mountpoint,
>  	.uninitialize_mountpoint = filelayout_uninitialize_mountpoint,
>  };
> diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
> new file mode 100644
> index 0000000..2467b5f
> --- /dev/null
> +++ b/fs/nfs/nfs4filelayout.h
> @@ -0,0 +1,74 @@
> +/*
> + *  NFSv4 file layout driver data structures.
> + *
> + *  Copyright (c) 2002 The Regents of the University of Michigan.
> + *  All rights reserved.
> + *
> + *  Dean Hildebrand   <dhildebz@umich.edu>
> + */
> +
> +#ifndef FS_NFS_NFS4FILELAYOUT_H
> +#define FS_NFS_NFS4FILELAYOUT_H
> +
> +#include "pnfs.h"
> +
> +/*
> + * Field testing shows we need to support upto 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
> +};
> +
> +/* Individual ip address */
> +struct nfs4_pnfs_ds {
> +	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
> +	u32			ds_ip_addr;
> +	u32			ds_port;
> +	struct nfs_client	*ds_clp;
> +	atomic_t		ds_count;
> +};
> +
> +struct nfs4_file_layout_dsaddr {
> +	struct nfs4_deviceid	deviceid;
> +	u32			stripe_count;
> +	u8			*stripe_indices;
> +	u32			ds_num;
> +	struct nfs4_pnfs_ds	*ds_list[1];
> +};
> +
> +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 pnfs_deviceid dev_id;
> +	unsigned int num_fh;
> +	struct nfs_fh *fh_array;
> +};
> +
> +static inline struct nfs4_filelayout_segment *
> +FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
> +{
> +	return container_of(lseg,
> +			    struct nfs4_filelayout_segment,
> +			    generic_hdr);
> +}
> +
> +extern void nfs4_fl_free_deviceid_callback(struct nfs4_deviceid *);
> +extern void print_ds(struct nfs4_pnfs_ds *ds);
> +extern void print_deviceid(struct pnfs_deviceid *dev_id);
> +extern struct nfs4_file_layout_dsaddr *
> +nfs4_fl_find_get_deviceid(struct nfs_client *, struct pnfs_deviceid *dev_id);
> +struct nfs4_file_layout_dsaddr *
> +get_device_info(struct inode *inode, struct pnfs_deviceid *dev_id);
> +
> +#endif /* FS_NFS_NFS4FILELAYOUT_H */
> diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
> new file mode 100644
> index 0000000..833ff9a
> --- /dev/null
> +++ b/fs/nfs/nfs4filelayoutdev.c
> @@ -0,0 +1,450 @@
> +/*
> + *  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 "internal.h"
> +#include "nfs4filelayout.h"
> +
> +#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
> +
> +/*
> + * Data server cache
> + *
> + * Data servers can be mapped to different device ids.
> + * nfs4_pnfs_ds reference counting
> + *   - set to 1 on allocation
> + *   - incremented when a device id maps a data server already in the cache.
> + *   - decremented when deviceid is removed from the cache.
> + */
> +DEFINE_SPINLOCK(nfs4_ds_cache_lock);
> +static LIST_HEAD(nfs4_data_server_cache);
> +
> +/* Debug routines */
> +void
> +print_ds(struct nfs4_pnfs_ds *ds)
> +{
> +	if (ds == NULL) {
> +		dprintk("%s NULL device\n", __func__);
> +		return;
> +	}
> +	dprintk("        ip_addr %x port %hu\n"
> +		"        ref count %d\n"
> +		"        client %p\n"
> +		"        cl_exchange_flags %x\n",
> +		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
> +		atomic_read(&ds->ds_count), ds->ds_clp,
> +		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
> +}
> +
> +void
> +print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
> +{
> +	int i;
> +
> +	dprintk("%s dsaddr->ds_num %d\n", __func__,
> +		dsaddr->ds_num);

Can we just do 1 test of ifdebug() at the beginning of this function
instead of doing the same test for each and every printk()?

> +	for (i = 0; i < dsaddr->ds_num; i++)
> +		print_ds(dsaddr->ds_list[i]);
> +}
> +
> +void print_deviceid(struct pnfs_deviceid *id)
> +{
> +	u32 *p = (u32 *)id;
> +
> +	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
> +		p[0], p[1], p[2], p[3]);
> +}
> +
> +/* nfs4_ds_cache_lock is held */
> +static struct nfs4_pnfs_ds *
> +_data_server_lookup_locked(u32 ip_addr, u32 port)
> +{
> +	struct nfs4_pnfs_ds *ds;
> +
> +	dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
> +			ntohl(ip_addr), ntohs(port));
> +
> +	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
> +		if (ds->ds_ip_addr == ip_addr &&
> +		    ds->ds_port == port) {
> +			return ds;
> +		}
> +	}
> +	return NULL;
> +}
> +
> +static void
> +destroy_ds(struct nfs4_pnfs_ds *ds)
> +{
> +	dprintk("--> %s\n", __func__);
> +	print_ds(ds);
> +
> +	if (ds->ds_clp)
> +		nfs_put_client(ds->ds_clp);
> +	kfree(ds);
> +}
> +
> +static void
> +nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
> +{
> +	struct nfs4_pnfs_ds *ds;
> +	int i;
> +
> +	print_deviceid(&dsaddr->deviceid.de_id);
> +
> +	for (i = 0; i < dsaddr->ds_num; i++) {
> +		ds = dsaddr->ds_list[i];
> +		if (ds != NULL) {
> +			if (atomic_dec_and_lock(&ds->ds_count,
> +						&nfs4_ds_cache_lock)) {
> +				list_del_init(&ds->ds_node);
> +				spin_unlock(&nfs4_ds_cache_lock);
> +				destroy_ds(ds);
> +			}
> +		}
> +	}
> +	kfree(dsaddr->stripe_indices);
> +	kfree(dsaddr);
> +}
> +
> +void
> +nfs4_fl_free_deviceid_callback(struct nfs4_deviceid *device)
> +{
> +	struct nfs4_file_layout_dsaddr *dsaddr =
> +		container_of(device, struct nfs4_file_layout_dsaddr, deviceid);
> +
> +	nfs4_fl_free_deviceid(dsaddr);
> +}
> +
> +static struct nfs4_pnfs_ds *
> +nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port)
> +{
> +	struct nfs4_pnfs_ds *tmp_ds, *ds;
> +
> +	ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL);
> +	if (!ds)
> +		goto out;
> +
> +	spin_lock(&nfs4_ds_cache_lock);
> +	tmp_ds = _data_server_lookup_locked(ip_addr, port);
> +	if (tmp_ds == NULL) {
> +		ds->ds_ip_addr = ip_addr;
> +		ds->ds_port = port;
> +		atomic_set(&ds->ds_count, 1);
> +		INIT_LIST_HEAD(&ds->ds_node);
> +		ds->ds_clp = NULL;
> +		list_add(&ds->ds_node, &nfs4_data_server_cache);
> +		dprintk("%s add new data server ip 0x%x\n", __func__,
> +			ds->ds_ip_addr);
> +	} else {
> +		kfree(ds);
> +		atomic_inc(&tmp_ds->ds_count);
> +		dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n",
> +			__func__, tmp_ds->ds_ip_addr,
> +			atomic_read(&tmp_ds->ds_count));
> +		ds = tmp_ds;
> +	}
> +	spin_unlock(&nfs4_ds_cache_lock);
> +out:
> +	return ds;
> +}
> +
> +/*
> + * Currently only support ipv4, and one multi-path address.
> + */
> +static struct nfs4_pnfs_ds *
> +decode_and_add_ds(__be32 **pp, struct inode *inode)
> +{
> +	struct nfs4_pnfs_ds *ds = NULL;
> +	char *buf;
> +	const char *ipend, *pstr;
> +	u32 ip_addr, port;
> +	int nlen, rlen, i;
> +	int tmp[2];
> +	__be32 *r_netid, *r_addr, *p = *pp;
> +
> +	/* r_netid */
> +	nlen = be32_to_cpup(p++);
> +	r_netid = p;
> +	p += XDR_QUADLEN(nlen);
> +
> +	/* r_addr */
> +	rlen = be32_to_cpup(p++);
> +	r_addr = p;
> +	p += XDR_QUADLEN(rlen);
> +	*pp = p;
> +
> +	/* Check that netid is "tcp" */
> +	if (nlen != 3 ||  memcmp((char *)r_netid, "tcp", 3)) {
> +		dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
> +		goto out_err;
> +	}
> +
> +	/* ipv6 length plus port is legal */
> +	if (rlen > INET6_ADDRSTRLEN + 8) {
> +		dprintk("%s Invalid address, length %d\n", __func__,
> +			rlen);
> +		goto out_err;
> +	}
> +	buf = kmalloc(rlen + 1, GFP_KERNEL);
> +	buf[rlen] = '\0';
> +	memcpy(buf, r_addr, rlen);
> +
> +	/* replace the port dots with dashes for the in4_pton() delimiter*/
> +	for (i = 0; i < 2; i++) {
> +		char *res = strrchr(buf, '.');
> +		*res = '-';
> +	}
> +
> +	/* Currently only support ipv4 address */
> +	if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) {
> +		dprintk("%s: Only ipv4 addresses supported\n", __func__);
> +		goto out_free;
> +	}
> +
> +	/* port */
> +	pstr = ipend;
> +	sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]);
> +	port = htons((tmp[0] << 8) | (tmp[1]));
> +
> +	ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
> +	dprintk("%s Decoded address and port %s\n", __func__, buf);
> +out_free:
> +	kfree(buf);
> +out_err:
> +	return ds;
> +}
> +
> +
> +
> +/*Decode opaque device data and return the result */
> +static struct nfs4_file_layout_dsaddr*
> +decode_device(struct inode *ino, struct pnfs_device *pdev)
> +{
> +	int i, dummy;
> +	u32 cnt, num;
> +	u8 *indexp;
> +	__be32 *p = (__be32 *)pdev->area, *indicesp;
> +	struct nfs4_file_layout_dsaddr *dsaddr;
> +
> +	/* Get the stripe count (number of stripe index) */
> +	cnt = be32_to_cpup(p++);
> +	dprintk("%s stripe count  %d\n", __func__, cnt);
> +	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
> +		printk(KERN_WARNING "%s: stripe count %d greater than "
> +		       "supported maximum %d\n", __func__,
> +			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
> +		goto out_err;
> +	}
> +
> +	/* Check the multipath list count */
> +	indicesp = p;
> +	p += XDR_QUADLEN(cnt << 2);
> +	num = be32_to_cpup(p++);
> +	dprintk("%s ds_num %u\n", __func__, num);
> +	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
> +		printk(KERN_WARNING "%s: multipath count %d greater than "
> +			"supported maximum %d\n", __func__,
> +			num, NFS4_PNFS_MAX_MULTI_CNT);
> +		goto out_err;
> +	}
> +	dsaddr = kzalloc(sizeof(*dsaddr) +
> +			(sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
> +			GFP_KERNEL);
> +	if (!dsaddr)
> +		goto out_err;
> +
> +	dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL);
> +	if (!dsaddr->stripe_indices)
> +		goto out_err_free;
> +
> +	dsaddr->stripe_count = cnt;
> +	dsaddr->ds_num = num;
> +
> +	memcpy(&dsaddr->deviceid.de_id, &pdev->dev_id, sizeof(pdev->dev_id));
> +
> +	/* Go back an read stripe indices */
> +	p = indicesp;
> +	indexp = &dsaddr->stripe_indices[0];
> +	for (i = 0; i < dsaddr->stripe_count; i++) {
> +		*indexp = be32_to_cpup(p++);
> +		if (*indexp >= num)
> +			goto out_err_free;
> +		indexp++;
> +	}
> +	/* Skip already read multipath list count */
> +	p++;
> +
> +	for (i = 0; i < dsaddr->ds_num; i++) {
> +		int j;
> +
> +		dummy = be32_to_cpup(p++); /* multipath count */
> +		if (dummy > 1) {
> +			printk(KERN_WARNING
> +			       "%s: Multipath count %d not supported, "
> +			       "skipping all greater than 1\n", __func__,
> +				dummy);
> +		}
> +		for (j = 0; j < dummy; j++) {
> +			if (j == 0) {
> +				dsaddr->ds_list[i] = decode_and_add_ds(&p, ino);
> +				if (dsaddr->ds_list[i] == NULL)
> +					goto out_err_free;
> +			} else {
> +				u32 len;
> +				/* skip extra multipath */
> +				len = be32_to_cpup(p++);
> +				p += XDR_QUADLEN(len);
> +				len = be32_to_cpup(p++);
> +				p += XDR_QUADLEN(len);
> +				continue;
> +			}
> +		}
> +	}
> +	nfs4_init_deviceid_node(&dsaddr->deviceid);
> +
> +	return dsaddr;
> +
> +out_err_free:
> +	nfs4_fl_free_deviceid(dsaddr);
> +out_err:
> +	dprintk("%s ERROR: returning NULL\n", __func__);
> +	return NULL;
> +}
> +
> +/*
> + * Decode the opaque device specified in 'dev'
> + * and add it to the list of available devices.
> + * If the deviceid is already cached, nfs4_add_deviceid will return
> + * a pointer to the cached struct and throw away the new.
> + */
> +static struct nfs4_file_layout_dsaddr*
> +decode_and_add_device(struct inode *inode, struct pnfs_device *dev)
> +{
> +	struct nfs4_file_layout_dsaddr *dsaddr;
> +	struct nfs4_deviceid *d;
> +
> +	dsaddr = decode_device(inode, dev);
> +	if (!dsaddr) {
> +		printk(KERN_WARNING "%s: Could not decode or add device\n",
> +			__func__);
> +		return NULL;
> +	}
> +
> +	d = nfs4_add_deviceid(NFS_SERVER(inode)->nfs_client->cl_devid_cache,
> +			      &dsaddr->deviceid);
> +
> +	return container_of(d, struct nfs4_file_layout_dsaddr, deviceid);
> +}
> +
> +/*
> + * Retrieve the information for dev_id, add it to the list
> + * of available devices, and return it.
> + */
> +struct nfs4_file_layout_dsaddr *
> +get_device_info(struct inode *inode, struct pnfs_deviceid *dev_id)
> +{
> +	struct pnfs_device *pdev = NULL;
> +	u32 max_resp_sz;
> +	int max_pages;
> +	struct page **pages = NULL;
> +	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
> +	int rc, i;
> +	struct nfs_server *server = NFS_SERVER(inode);
> +
> +	/*
> +	 * Use the session max response size as the basis for setting
> +	 * GETDEVICEINFO's maxcount
> +	 */
> +	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
> +	max_pages = max_resp_sz >> PAGE_SHIFT;
> +	dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
> +		__func__, inode, max_resp_sz, max_pages);
> +
> +	pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL);
> +	if (pdev == NULL)
> +		return NULL;
> +
> +	pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL);
> +	if (pages == NULL) {
> +		kfree(pdev);
> +		return NULL;
> +	}
> +	for (i = 0; i < max_pages; i++) {
> +		pages[i] = alloc_page(GFP_KERNEL);
> +		if (!pages[i])
> +			goto out_free;
> +	}
> +
> +	/* set pdev->area */
> +	pdev->area = vmap(pages, max_pages, VM_MAP, PAGE_KERNEL);
> +	if (!pdev->area)
> +		goto out_free;
> +
> +	memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
> +	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
> +	pdev->pages = pages;
> +	pdev->pgbase = 0;
> +	pdev->pglen = PAGE_SIZE * max_pages;
> +	pdev->mincount = 0;
> +	/* TODO: Update types when CB_NOTIFY_DEVICEID is available */
> +	pdev->dev_notify_types = 0;
> +
> +	rc = nfs4_proc_getdeviceinfo(server, pdev);
> +	dprintk("%s getdevice info returns %d\n", __func__, rc);
> +	if (rc)
> +		goto out_free;
> +
> +	/*
> +	 * Found new device, need to decode it and then add it to the
> +	 * list of known devices for this mountpoint.
> +	 */
> +	dsaddr = decode_and_add_device(inode, pdev);
> +out_free:
> +	if (pdev->area != NULL)
> +		vunmap(pdev->area);
> +	for (i = 0; i < max_pages; i++)
> +		__free_page(pages[i]);
> +	kfree(pages);
> +	kfree(pdev);
> +	dprintk("<-- %s dsaddr %p\n", __func__, dsaddr);
> +	return dsaddr;
> +}
> +
> +struct nfs4_file_layout_dsaddr *
> +nfs4_fl_find_get_deviceid(struct nfs_client *clp, struct pnfs_deviceid *id)
> +{
> +	struct nfs4_deviceid *d;
> +
> +	d = nfs4_find_get_deviceid(clp->cl_devid_cache, id);
> +	return (d == NULL) ? NULL :
> +		container_of(d, struct nfs4_file_layout_dsaddr, deviceid);
> +}