From: "J. Bruce Fields" <bfields@fieldses.org>
To: NeilBrown <neilb@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>,
Josef Bacik <josef@toxicpanda.com>,
Chuck Lever <chuck.lever@oracle.com>, Chris Mason <clm@fb.com>,
David Sterba <dsterba@suse.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, linux-nfs@vger.kernel.org,
linux-btrfs@vger.kernel.org
Subject: Re: [PATCH 09/11] nfsd: Allow filehandle lookup to cross internal mount points.
Date: Wed, 28 Jul 2021 15:15:39 -0400 [thread overview]
Message-ID: <20210728191539.GB3152@fieldses.org> (raw)
In-Reply-To: <162742546556.32498.16708762469227881912.stgit@noble.brown>
On Wed, Jul 28, 2021 at 08:37:45AM +1000, NeilBrown wrote:
> Enhance nfsd to detect internal mounts and to cross them without
> requiring a new export.
Why don't we want a new export?
(Honest question, it's not obvious to me what the best behavior is.)
--b.
>
> Also ensure the fsid reported is different for different submounts. We
> do this by xoring in the ino of the mounted-on directory. This makes
> sense for btrfs at least.
>
> Signed-off-by: NeilBrown <neilb@suse.de>
> ---
> fs/nfsd/nfs3xdr.c | 28 +++++++++++++++++++++-------
> fs/nfsd/nfs4xdr.c | 34 +++++++++++++++++++++++-----------
> fs/nfsd/nfsfh.c | 7 ++++++-
> fs/nfsd/vfs.c | 11 +++++++++--
> 4 files changed, 59 insertions(+), 21 deletions(-)
>
> diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
> index 67af0c5c1543..80b1cc0334fa 100644
> --- a/fs/nfsd/nfs3xdr.c
> +++ b/fs/nfsd/nfs3xdr.c
> @@ -370,6 +370,8 @@ svcxdr_encode_fattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
> case FSIDSOURCE_UUID:
> fsid = ((u64 *)fhp->fh_export->ex_uuid)[0];
> fsid ^= ((u64 *)fhp->fh_export->ex_uuid)[1];
> + if (fhp->fh_mnt != fhp->fh_export->ex_path.mnt)
> + fsid ^= nfsd_get_mounted_on(fhp->fh_mnt);
> break;
> default:
> fsid = (u64)huge_encode_dev(fhp->fh_dentry->d_sb->s_dev);
> @@ -1094,8 +1096,8 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
> __be32 rv = nfserr_noent;
>
> dparent = cd->fh.fh_dentry;
> - exp = cd->fh.fh_export;
> - child.mnt = cd->fh.fh_mnt;
> + exp = exp_get(cd->fh.fh_export);
> + child.mnt = mntget(cd->fh.fh_mnt);
>
> if (isdotent(name, namlen)) {
> if (namlen == 2) {
> @@ -1112,15 +1114,27 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
> child.dentry = dget(dparent);
> } else
> child.dentry = lookup_positive_unlocked(name, dparent, namlen);
> - if (IS_ERR(child.dentry))
> + if (IS_ERR(child.dentry)) {
> + mntput(child.mnt);
> + exp_put(exp);
> return rv;
> - if (d_mountpoint(child.dentry))
> - goto out;
> - if (child.dentry->d_inode->i_ino != ino)
> + }
> + /* If child is a mountpoint, then we want to expose the fact
> + * so client can create a mountpoint. If not, then a different
> + * ino number probably means a race with rename, so avoid providing
> + * too much detail.
> + */
> + if (nfsd_mountpoint(child.dentry, exp)) {
> + int err;
> + err = nfsd_cross_mnt(cd->rqstp, &child, &exp);
> + if (err)
> + goto out;
> + } else if (child.dentry->d_inode->i_ino != ino)
> goto out;
> rv = fh_compose(fhp, exp, &child, &cd->fh);
> out:
> - dput(child.dentry);
> + path_put(&child);
> + exp_put(exp);
> return rv;
> }
>
> diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
> index d5683b6a74b2..4dbc99ed2c8b 100644
> --- a/fs/nfsd/nfs4xdr.c
> +++ b/fs/nfsd/nfs4xdr.c
> @@ -2817,6 +2817,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
> struct kstat stat;
> struct svc_fh *tempfh = NULL;
> struct kstatfs statfs;
> + u64 mounted_on_ino;
> + u64 sub_fsid;
> __be32 *p;
> int starting_len = xdr->buf->len;
> int attrlen_offset;
> @@ -2871,6 +2873,24 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
> goto out;
> fhp = tempfh;
> }
> + if ((bmval0 & FATTR4_WORD0_FSID) ||
> + (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID)) {
> + mounted_on_ino = stat.ino;
> + sub_fsid = 0;
> + /*
> + * The inode number that the current mnt is mounted on is
> + * used for MOUNTED_ON_FILED if we are at the root,
> + * and for sub_fsid if mnt is not the export mnt.
> + */
> + if (ignore_crossmnt == 0) {
> + u64 moi = nfsd_get_mounted_on(mnt);
> +
> + if (dentry == mnt->mnt_root && moi)
> + mounted_on_ino = moi;
> + if (mnt != exp->ex_path.mnt)
> + sub_fsid = moi;
> + }
> + }
> if (bmval0 & FATTR4_WORD0_ACL) {
> err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl);
> if (err == -EOPNOTSUPP)
> @@ -3008,6 +3028,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
> case FSIDSOURCE_UUID:
> p = xdr_encode_opaque_fixed(p, exp->ex_uuid,
> EX_UUID_LEN);
> + if (mnt != exp->ex_path.mnt)
> + *(u64*)(p-2) ^= sub_fsid;
> break;
> }
> }
> @@ -3253,20 +3275,10 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
> *p++ = cpu_to_be32(stat.mtime.tv_nsec);
> }
> if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
> - u64 ino;
> -
> p = xdr_reserve_space(xdr, 8);
> if (!p)
> goto out_resource;
> - /*
> - * Get parent's attributes if not ignoring crossmount
> - * and this is the root of a cross-mounted filesystem.
> - */
> - if (ignore_crossmnt == 0 && dentry == mnt->mnt_root)
> - ino = nfsd_get_mounted_on(mnt);
> - if (!ino)
> - ino = stat.ino;
> - p = xdr_encode_hyper(p, ino);
> + p = xdr_encode_hyper(p, mounted_on_ino);
> }
> #ifdef CONFIG_NFSD_PNFS
> if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) {
> diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
> index 4023046f63e2..4b53838bca89 100644
> --- a/fs/nfsd/nfsfh.c
> +++ b/fs/nfsd/nfsfh.c
> @@ -9,7 +9,7 @@
> */
>
> #include <linux/exportfs.h>
> -
> +#include <linux/namei.h>
> #include <linux/sunrpc/svcauth_gss.h>
> #include "nfsd.h"
> #include "vfs.h"
> @@ -285,6 +285,11 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
> default:
> dentry = ERR_PTR(-ESTALE);
> }
> + } else if (nfsd_mountpoint(dentry, exp)) {
> + struct path path = { .mnt = mnt, .dentry = dentry };
> + follow_down(&path, LOOKUP_AUTOMOUNT);
> + mnt = path.mnt;
> + dentry = path.dentry;
> }
> }
> if (dentry == NULL)
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index baa12ac36ece..22523e1cd478 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -64,7 +64,7 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct path *path_parent,
> .dentry = dget(path_parent->dentry)};
> int err = 0;
>
> - err = follow_down(&path, 0);
> + err = follow_down(&path, LOOKUP_AUTOMOUNT);
> if (err < 0)
> goto out;
> if (path.mnt == path_parent->mnt && path.dentry == path_parent->dentry &&
> @@ -73,6 +73,13 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct path *path_parent,
> path_put(&path);
> goto out;
> }
> + if (mount_is_internal(path.mnt)) {
> + /* Use the new path, but don't look for a new export */
> + /* FIXME should I check NOHIDE in this case?? */
> + path_put(path_parent);
> + *path_parent = path;
> + goto out;
> + }
>
> exp2 = rqst_exp_get_by_name(rqstp, &path);
> if (IS_ERR(exp2)) {
> @@ -157,7 +164,7 @@ int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
> return 1;
> if (nfsd4_is_junction(dentry))
> return 1;
> - if (d_mountpoint(dentry))
> + if (d_managed(dentry))
> /*
> * Might only be a mountpoint in a different namespace,
> * but we need to check.
>
next prev parent reply other threads:[~2021-07-28 19:15 UTC|newest]
Thread overview: 122+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-27 22:37 [PATCH/RFC 00/11] expose btrfs subvols in mount table correctly NeilBrown
2021-07-27 22:37 ` [PATCH 07/11] exportfs: Allow filehandle lookup to cross internal mount points NeilBrown
2021-07-28 10:13 ` Amir Goldstein
2021-07-29 0:28 ` NeilBrown
2021-07-29 5:27 ` Amir Goldstein
2021-08-06 7:52 ` Miklos Szeredi
2021-08-06 8:08 ` Amir Goldstein
2021-08-06 8:18 ` Miklos Szeredi
2021-07-28 19:17 ` J. Bruce Fields
2021-07-28 22:25 ` NeilBrown
2021-07-27 22:37 ` [PATCH 04/11] VFS: export lookup_mnt() NeilBrown
2021-07-30 0:31 ` Al Viro
2021-07-30 5:33 ` NeilBrown
2021-07-27 22:37 ` [PATCH 01/11] VFS: show correct dev num in mountinfo NeilBrown
2021-07-30 0:25 ` Al Viro
2021-07-30 5:28 ` NeilBrown
2021-07-30 5:54 ` Miklos Szeredi
2021-07-30 6:13 ` NeilBrown
2021-07-30 7:18 ` Miklos Szeredi
2021-07-30 7:33 ` NeilBrown
2021-07-30 7:59 ` Miklos Szeredi
2021-08-02 4:18 ` A Third perspective on BTRFS nfsd subvol dev/inode number issues NeilBrown
2021-08-02 5:25 ` Al Viro
2021-08-02 5:40 ` NeilBrown
2021-08-02 7:54 ` Amir Goldstein
2021-08-02 13:53 ` Josef Bacik
2021-08-03 22:29 ` Qu Wenruo
2021-08-02 14:47 ` Frank Filz
2021-08-02 21:24 ` NeilBrown
2021-08-02 7:15 ` Martin Steigerwald
2021-08-02 21:40 ` NeilBrown
2021-08-02 12:39 ` J. Bruce Fields
2021-08-02 20:32 ` Patrick Goetz
2021-08-02 20:41 ` J. Bruce Fields
2021-08-02 21:10 ` NeilBrown
2021-08-02 21:50 ` J. Bruce Fields
2021-08-02 21:59 ` NeilBrown
2021-08-02 22:14 ` J. Bruce Fields
2021-08-02 22:36 ` NeilBrown
2021-08-03 0:15 ` J. Bruce Fields
2021-07-27 22:37 ` [PATCH 03/11] VFS: pass lookup_flags into follow_down() NeilBrown
2021-07-27 22:37 ` [PATCH 11/11] btrfs: use automount to bind-mount all subvol roots NeilBrown
2021-07-28 8:37 ` kernel test robot
2021-07-28 8:37 ` [RFC PATCH] btrfs: btrfs_mountpoint_expiry_timeout can be static kernel test robot
2021-07-28 13:12 ` [PATCH 11/11] btrfs: use automount to bind-mount all subvol roots Christian Brauner
2021-07-29 0:43 ` NeilBrown
2021-07-29 14:38 ` Christian Brauner
2021-07-31 6:25 ` [btrfs] 5874902268: xfstests.btrfs.202.fail kernel test robot
2021-07-27 22:37 ` [PATCH 06/11] nfsd: include a vfsmount in struct svc_fh NeilBrown
2021-07-27 22:37 ` [PATCH 10/11] btrfs: introduce mapping function from location to inum NeilBrown
2021-07-27 22:37 ` [PATCH 02/11] VFS: allow d_automount to create in-place bind-mount NeilBrown
2021-07-27 22:37 ` [PATCH 09/11] nfsd: Allow filehandle lookup to cross internal mount points NeilBrown
2021-07-28 19:15 ` J. Bruce Fields [this message]
2021-07-28 22:29 ` NeilBrown
2021-07-30 0:42 ` Al Viro
2021-07-30 5:43 ` NeilBrown
2021-07-27 22:37 ` [PATCH 08/11] nfsd: change get_parent_attributes() to nfsd_get_mounted_on() NeilBrown
2021-07-27 22:37 ` [PATCH 05/11] VFS: new function: mount_is_internal() NeilBrown
2021-07-28 2:16 ` Al Viro
2021-07-28 3:32 ` NeilBrown
2021-07-30 0:34 ` Al Viro
2021-07-28 2:19 ` [PATCH/RFC 00/11] expose btrfs subvols in mount table correctly Al Viro
2021-07-28 4:58 ` Wang Yugui
2021-07-28 6:04 ` Wang Yugui
2021-07-28 7:01 ` NeilBrown
2021-07-28 12:26 ` Neal Gompa
2021-07-28 19:14 ` J. Bruce Fields
2021-07-29 1:29 ` Zygo Blaxell
2021-07-29 1:43 ` NeilBrown
2021-07-29 23:20 ` Zygo Blaxell
2021-07-28 22:50 ` NeilBrown
2021-07-29 2:37 ` Zygo Blaxell
2021-07-29 3:36 ` NeilBrown
2021-07-29 23:20 ` Zygo Blaxell
2021-07-30 2:36 ` NeilBrown
2021-07-30 5:25 ` Qu Wenruo
2021-07-30 5:31 ` Qu Wenruo
2021-07-30 5:53 ` Amir Goldstein
2021-07-30 6:00 ` NeilBrown
2021-07-30 6:09 ` Qu Wenruo
2021-07-30 5:58 ` NeilBrown
2021-07-30 6:23 ` Qu Wenruo
2021-07-30 6:53 ` NeilBrown
2021-07-30 7:09 ` Qu Wenruo
2021-07-30 18:15 ` Zygo Blaxell
2021-07-30 15:17 ` J. Bruce Fields
2021-07-30 15:48 ` Josef Bacik
2021-07-30 16:25 ` Forza
2021-07-30 17:43 ` Zygo Blaxell
2021-07-30 5:28 ` Amir Goldstein
2021-07-28 13:43 ` g.btrfs
2021-07-29 1:39 ` NeilBrown
2021-07-29 9:28 ` Graham Cobb
2021-07-28 7:06 ` NeilBrown
2021-07-28 9:36 ` Wang Yugui
2021-07-28 19:35 ` J. Bruce Fields
2021-07-28 21:30 ` Josef Bacik
2021-07-30 0:13 ` Al Viro
2021-07-30 6:08 ` NeilBrown
2021-08-13 1:45 ` [PATCH] VFS/BTRFS/NFSD: provide more unique inode number for btrfs export NeilBrown
2021-08-13 14:55 ` Josef Bacik
2021-08-15 7:39 ` Goffredo Baroncelli
2021-08-15 19:35 ` Roman Mamedov
2021-08-15 21:03 ` Goffredo Baroncelli
2021-08-15 21:53 ` NeilBrown
2021-08-17 19:34 ` Goffredo Baroncelli
2021-08-17 21:39 ` NeilBrown
2021-08-18 17:24 ` Goffredo Baroncelli
2021-08-15 22:17 ` NeilBrown
2021-08-19 8:01 ` Amir Goldstein
2021-08-20 3:21 ` NeilBrown
2021-08-20 6:23 ` Amir Goldstein
2021-08-23 4:05 ` [PATCH v2] BTRFS/NFSD: " NeilBrown
2021-08-18 14:54 ` [PATCH] VFS/BTRFS/NFSD: " Wang Yugui
2021-08-18 21:46 ` NeilBrown
2021-08-19 2:19 ` Zygo Blaxell
2021-08-20 2:54 ` NeilBrown
2021-08-22 19:29 ` Zygo Blaxell
2021-08-23 5:51 ` NeilBrown
2021-08-23 23:22 ` NeilBrown
2021-08-25 2:06 ` Zygo Blaxell
2021-08-23 0:57 ` Wang Yugui
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210728191539.GB3152@fieldses.org \
--to=bfields@fieldses.org \
--cc=chuck.lever@oracle.com \
--cc=clm@fb.com \
--cc=dsterba@suse.com \
--cc=hch@infradead.org \
--cc=josef@toxicpanda.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neilb@suse.de \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).