Re: [V3 2/2] nfsd: Add a super simple flex file server

[Tom Haynes <loghyr@excfb.com>]

On Tue, May 31, 2016 at 05:42:15PM +0200, Mkrtchyan, Tigran wrote:
> 
> 
> ----- Original Message -----
> > From: "Tom Haynes" <thomas.haynes@primarydata.com>
> > To: "J. Bruce Fields" <bfields@fieldses.org>
> > Cc: "Linux NFS Mailing list" <linux-nfs@vger.kernel.org>, "Christoph Hellwig" <hch@lst.de>
> > Sent: Thursday, May 26, 2016 7:05:11 PM
> > Subject: [V3 2/2] nfsd: Add a super simple flex file server
> 
> > Have a simple flex file server where the mds (NFSv4.1 or NFSv4.2)
> > is also the ds (NFSv3). I.e., the metadata and the data file are
> > the exact same file.
> > 
> > This will allow testing of the flex file client.
> > 
> > Simply add the "pnfs" export option to your export
> > in /etc/exports and mount from a client that supports
> > flex files.
> > 
> > Signed-off-by: Tom Haynes <loghyr@primarydata.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > ---
> > fs/nfsd/Kconfig             |  17 ++++++
> > fs/nfsd/Makefile            |   1 +
> > fs/nfsd/flexfilelayout.c    | 133 ++++++++++++++++++++++++++++++++++++++++++++
> > fs/nfsd/flexfilelayoutxdr.c | 115 ++++++++++++++++++++++++++++++++++++++
> > fs/nfsd/flexfilelayoutxdr.h |  49 ++++++++++++++++
> > fs/nfsd/nfs4layouts.c       |  12 +++-
> > fs/nfsd/pnfs.h              |   3 +
> > 7 files changed, 329 insertions(+), 1 deletion(-)
> > create mode 100644 fs/nfsd/flexfilelayout.c
> > create mode 100644 fs/nfsd/flexfilelayoutxdr.c
> > create mode 100644 fs/nfsd/flexfilelayoutxdr.h
> > 
> > diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
> > index c9f583d..e64d1a3 100644
> > --- a/fs/nfsd/Kconfig
> > +++ b/fs/nfsd/Kconfig
> > @@ -111,6 +111,23 @@ config NFSD_SCSILAYOUT
> > 
> > 	  If unsure, say N.
> > 
> > +config NFSD_FLEXFILELAYOUT
> > +	bool "NFSv4.1 server support for pNFS Flex File layouts"
> > +	depends on NFSD_V4
> > +	select NFSD_PNFS
> > +	help
> > +	  This option enables support for the exporting pNFS Flex File
> > +	  layouts in the kernel's NFS server. The pNFS Flex File  layout
> > +	  enables NFS clients to directly perform I/O to NFSv3 devices
> > +	  accesible to both the server and the clients.  See
> > +	  draft-ietf-nfsv4-flex-files for more details.
> > +
> > +	  Warning, this server implements the bare minimum functionality
> > +	  to be a flex file server - it is for testing the client,
> > +	  not for use in production.
> > +
> > +	  If unsure, say N.
> > +
> > config NFSD_V4_SECURITY_LABEL
> > 	bool "Provide Security Label support for NFSv4 server"
> > 	depends on NFSD_V4 && SECURITY
> > diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
> > index 3ae5f3c..5f5d3a7 100644
> > --- a/fs/nfsd/Makefile
> > +++ b/fs/nfsd/Makefile
> > @@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o
> > nfs4idmap.o \
> > nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
> > nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
> > nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
> > +nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
> > diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
> > new file mode 100644
> > index 0000000..df880e9
> > --- /dev/null
> > +++ b/fs/nfsd/flexfilelayout.c
> > @@ -0,0 +1,133 @@
> > +/*
> > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
> > + *
> > + * The following implements a super-simple flex-file server
> > + * where the NFSv4.1 mds is also the ds. And the storage is
> > + * the same. I.e., writing to the mds via a NFSv4.1 WRITE
> > + * goes to the same location as the NFSv3 WRITE.
> > + */
> > +#include <linux/slab.h>
> > +
> > +#include <linux/nfsd/debug.h>
> > +
> > +#include <linux/sunrpc/addr.h>
> > +
> > +#include "flexfilelayoutxdr.h"
> > +#include "pnfs.h"
> > +
> > +#define NFSDDBG_FACILITY	NFSDDBG_PNFS
> > +
> > +static __be32
> > +nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
> > +		struct nfsd4_layoutget *args)
> > +{
> > +	struct nfsd4_layout_seg *seg = &args->lg_seg;
> > +	u32 device_generation = 0;
> > +	int error;
> > +	uid_t u;
> > +
> > +	struct pnfs_ff_layout *fl;
> > +
> > +	/*
> > +	 * The super simple flex file server has 1 mirror, 1 data server,
> > +	 * and 1 file handle. So instead of 4 allocs, do 1 for now.
> > +	 * Zero it out for the stateid - don't want junk in there!
> > +	 */
> > +	error = -ENOMEM;
> > +	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
> > +	if (!fl)
> > +		goto out_error;
> > +	args->lg_content = fl;
> > +
> > +	/*
> > +	 * Avoid layout commit, try to force the I/O to the DS,
> > +	 * and for fun, cause all IOMODE_RW layout segments to
> > +	 * effectively be WRITE only.
> > +	 */
> > +	fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS |
> > +		    FF_FLAGS_NO_READ_IO;
> > +
> > +	/* Do not allow a IOMODE_READ segment to have write pemissions */
> > +	if (seg->iomode == IOMODE_READ) {
> > +		u = from_kuid(&init_user_ns, inode->i_uid) + 1;
> > +		fl->uid = make_kuid(&init_user_ns, u);
> > +	} else
> > +		fl->uid = inode->i_uid;
> > +	fl->gid = inode->i_gid;
> > +
> > +	error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation);
> > +	if (error)
> > +		goto out_error;
> > +
> > +	fl->fh.size = fhp->fh_handle.fh_size;
> > +	memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
> > +
> > +	/* Give whole file layout segments */
> > +	seg->offset = 0;
> > +	seg->length = NFS4_MAX_UINT64;
> > +
> > +	dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length,
> > +		seg->iomode);
> > +	return 0;
> > +
> > +out_error:
> > +	seg->length = 0;
> > +	return nfserrno(error);
> > +}
> > +
> > +static __be32
> > +nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
> > +		struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp)
> > +{
> > +	struct pnfs_ff_device_addr *da;
> > +
> > +	u16 port;
> > +	char addr[INET6_ADDRSTRLEN];
> > +
> > +	da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL);
> > +	if (!da)
> > +		return nfserrno(-ENOMEM);
> > +
> > +	gdp->gd_device = da;
> > +
> > +	da->version = 3;
> > +	da->minor_version = 0;
> > +
> > +	da->rsize = svc_max_payload(rqstp);
> > +	da->wsize = da->rsize;
> > +
> > +	rpc_ntop((struct sockaddr *)&rqstp->rq_daddr,
> > +		 addr, INET6_ADDRSTRLEN);
> > +	if (rqstp->rq_daddr.ss_family == AF_INET) {
> > +		struct sockaddr_in *sin;
> > +
> > +		sin = (struct sockaddr_in *)&rqstp->rq_daddr;
> > +		port = ntohs(sin->sin_port);
> > +		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp");
> > +		da->netaddr.netid_len = 3;
> > +	} else {
> > +		struct sockaddr_in6 *sin6;
> > +
> > +		sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr;
> > +		port = ntohs(sin6->sin6_port);
> > +		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6");
> > +		da->netaddr.netid_len = 4;
> > +	}
> > +
> > +	da->netaddr.addr_len =
> > +		snprintf(da->netaddr.addr, FF_ADDR_LEN + 1,
> > +			 "%s.%hhu.%hhu", addr, port >> 8, port & 0xff);
> > +
> > +	da->tightly_coupled = false;
> > +
> > +	return 0;
> > +}
> > +
> > +const struct nfsd4_layout_ops ff_layout_ops = {
> > +	.notify_types		=
> > +			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
> > +	.proc_getdeviceinfo	= nfsd4_ff_proc_getdeviceinfo,
> > +	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
> > +	.proc_layoutget		= nfsd4_ff_proc_layoutget,
> > +	.encode_layoutget	= nfsd4_ff_encode_layoutget,
> > +};
> > diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c
> > new file mode 100644
> > index 0000000..a241f29
> > --- /dev/null
> > +++ b/fs/nfsd/flexfilelayoutxdr.c
> > @@ -0,0 +1,115 @@
> > +/*
> > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
> > + */
> > +#include <linux/sunrpc/svc.h>
> > +#include <linux/nfs4.h>
> > +
> > +#include "nfsd.h"
> > +#include "flexfilelayoutxdr.h"
> > +
> > +#define NFSDDBG_FACILITY	NFSDDBG_PNFS
> > +
> > +struct ff_idmap {
> > +	char buf[11];
> > +	int len;
> > +};
> > +
> > +__be32
> > +nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
> > +		struct nfsd4_layoutget *lgp)
> > +{
> > +	struct pnfs_ff_layout *fl = lgp->lg_content;
> > +	int len, mirror_len, ds_len, fh_len;
> > +	__be32 *p;
> > +
> > +	/*
> > +	 * Unlike nfsd4_encode_user, we know these will
> > +	 * always be stringified.
> > +	 */
> > +	struct ff_idmap uid;
> > +	struct ff_idmap gid;
> > +
> > +	fh_len = 4 + fl->fh.size;
> > +
> > +	uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid));
> > +	gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid));
> > +
> > +	/* 8 + len for recording the length, name, and padding */
> > +	ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len +
> > +		 8 + uid.len + 8 + gid.len;
> > +
> > +	mirror_len = 4 + ds_len;
> > +
> > +	/* The layout segment */
> > +	len = 20 + mirror_len;
> > +
> > +	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
> > +	if (!p)
> > +		return nfserr_toosmall;
> > +
> > +	*p++ = cpu_to_be32(len);
> > +	p = xdr_encode_hyper(p, 1);		/* stripe unit of 1 */
> 
> 
> from flexfiles draft8:
> 
> If the number of stripes is one, then the value for ffl_stripe_unit
> MUST default to  zero. 
> 
> or I am treating the spec wrongly.

No, I'll fix that up.

Note that client is evidently not checking this value. :-)


> 
> Tigran.
> 
> > +
> > +	*p++ = cpu_to_be32(1);			/* single mirror */
> > +	*p++ = cpu_to_be32(1);			/* single data server */
> > +
> > +	p = xdr_encode_opaque_fixed(p, &fl->deviceid,
> > +			sizeof(struct nfsd4_deviceid));
> > +
> > +	*p++ = cpu_to_be32(1);			/* efficiency */
> > +
> > +	*p++ = cpu_to_be32(fl->stateid.si_generation);
> > +	p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque,
> > +				    sizeof(stateid_opaque_t));
> > +
> > +	*p++ = cpu_to_be32(1);			/* single file handle */
> > +	p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size);
> > +
> > +	p = xdr_encode_opaque(p, uid.buf, uid.len);
> > +	p = xdr_encode_opaque(p, gid.buf, gid.len);
> > +
> > +	*p++ = cpu_to_be32(fl->flags);
> > +	*p++ = cpu_to_be32(0);			/* No stats collect hint */
> > +
> > +	return 0;
> > +}
> > +
> > +__be32
> > +nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
> > +		struct nfsd4_getdeviceinfo *gdp)
> > +{
> > +	struct pnfs_ff_device_addr *da = gdp->gd_device;
> > +	int len;
> > +	int ver_len;
> > +	int addr_len;
> > +	__be32 *p;
> > +
> > +	/* len + padding for two strings */
> > +	addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len;
> > +	ver_len = 20;
> > +
> > +	len = 4 + ver_len + 4 + addr_len;
> > +
> > +	p = xdr_reserve_space(xdr, len + sizeof(__be32));
> > +	if (!p)
> > +		return nfserr_resource;
> > +
> > +	/*
> > +	 * Fill in the overall length and number of volumes at the beginning
> > +	 * of the layout.
> > +	 */
> > +	*p++ = cpu_to_be32(len);
> > +	*p++ = cpu_to_be32(1);			/* 1 netaddr */
> > +	p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len);
> > +	p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len);
> > +
> > +	*p++ = cpu_to_be32(1);			/* 1 versions */
> > +
> > +	*p++ = cpu_to_be32(da->version);
> > +	*p++ = cpu_to_be32(da->minor_version);
> > +	*p++ = cpu_to_be32(da->rsize);
> > +	*p++ = cpu_to_be32(da->wsize);
> > +	*p++ = cpu_to_be32(da->tightly_coupled);
> > +
> > +	return 0;
> > +}
> > diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h
> > new file mode 100644
> > index 0000000..b77275c
> > --- /dev/null
> > +++ b/fs/nfsd/flexfilelayoutxdr.h
> > @@ -0,0 +1,49 @@
> > +/*
> > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
> > + */
> > +#ifndef _NFSD_FLEXFILELAYOUTXDR_H
> > +#define _NFSD_FLEXFILELAYOUTXDR_H 1
> > +
> > +#include <linux/inet.h>
> > +#include "xdr4.h"
> > +
> > +#define FF_FLAGS_NO_LAYOUTCOMMIT 1
> > +#define FF_FLAGS_NO_IO_THRU_MDS  2
> > +#define FF_FLAGS_NO_READ_IO      4
> > +
> > +struct xdr_stream;
> > +
> > +#define FF_NETID_LEN		(4)
> > +#define FF_ADDR_LEN		(INET6_ADDRSTRLEN + 1)
> > +struct pnfs_ff_netaddr {
> > +	char				netid[FF_NETID_LEN + 1];
> > +	char				addr[FF_ADDR_LEN + 1];
> > +	u32				netid_len;
> > +	u32				addr_len;
> > +};
> > +
> > +struct pnfs_ff_device_addr {
> > +	struct pnfs_ff_netaddr		netaddr;
> > +	u32				version;
> > +	u32				minor_version;
> > +	u32				rsize;
> > +	u32				wsize;
> > +	bool				tightly_coupled;
> > +};
> > +
> > +struct pnfs_ff_layout {
> > +	u32				flags;
> > +	u32				stats_collect_hint;
> > +	kuid_t				uid;
> > +	kgid_t				gid;
> > +	struct nfsd4_deviceid		deviceid;
> > +	stateid_t			stateid;
> > +	struct nfs_fh			fh;
> > +};
> > +
> > +__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
> > +		struct nfsd4_getdeviceinfo *gdp);
> > +__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
> > +		struct nfsd4_layoutget *lgp);
> > +
> > +#endif /* _NFSD_FLEXFILELAYOUTXDR_H */
> > diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
> > index 825c7bc..8fee9bf 100644
> > --- a/fs/nfsd/nfs4layouts.c
> > +++ b/fs/nfsd/nfs4layouts.c
> > @@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
> > static const struct lock_manager_operations nfsd4_layouts_lm_ops;
> > 
> > const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
> > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT
> > +	[LAYOUT_FLEX_FILES]	= &ff_layout_ops,
> > +#endif
> > #ifdef CONFIG_NFSD_BLOCKLAYOUT
> > 	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
> > #endif
> > @@ -122,17 +125,24 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct
> > svc_fh *fhp,
> > 
> > void nfsd4_setup_layout_type(struct svc_export *exp)
> > {
> > +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
> > 	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
> > +#endif
> > 
> > 	if (!(exp->ex_flags & NFSEXP_PNFS))
> > 		return;
> > 
> > 	/*
> > -	 * Check if the file system supports exporting a block-like layout.
> > +	 * If flex file is configured, use it by default. Otherwise
> > +	 * check if the file system supports exporting a block-like layout.
> > 	 * If the block device supports reservations prefer the SCSI layout,
> > 	 * otherwise advertise the block layout.
> > 	 */
> > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT
> > +	exp->ex_layout_type = LAYOUT_FLEX_FILES;
> > +#endif
> > #ifdef CONFIG_NFSD_BLOCKLAYOUT
> > +	/* overwrite flex file layout selection if needed */
> > 	if (sb->s_export_op->get_uuid &&
> > 	    sb->s_export_op->map_blocks &&
> > 	    sb->s_export_op->commit_blocks)
> > diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
> > index e855677..0c2a716 100644
> > --- a/fs/nfsd/pnfs.h
> > +++ b/fs/nfsd/pnfs.h
> > @@ -45,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops;
> > #ifdef CONFIG_NFSD_SCSILAYOUT
> > extern const struct nfsd4_layout_ops scsi_layout_ops;
> > #endif
> > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT
> > +extern const struct nfsd4_layout_ops ff_layout_ops;
> > +#endif
> > 
> > __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
> > 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
> > --
> > 1.8.3.1
> > 
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html