On Wed, 06 May 2015 21:21:15 +0800 Kinglong Mee <kinglongmee@xxxxxxxxx> wrote:
> If there are some mount points(not exported for nfs) under pseudo root,
> after client's operation of those entry under the root, anyone *can't*
> unmount those mount points until export cache expired.
>
> # cat /etc/exports
> /nfs/xfs *(rw,insecure,no_subtree_check,no_root_squash)
> /nfs/pnfs *(rw,insecure,no_subtree_check,no_root_squash)
> # ll /nfs/
> total 0
> drwxr-xr-x. 3 root root 84 Apr 21 22:27 pnfs
> drwxr-xr-x. 3 root root 84 Apr 21 22:27 test
> drwxr-xr-x. 2 root root 6 Apr 20 22:01 xfs
> # mount /dev/sde /nfs/test
> # df
> Filesystem 1K-blocks Used Available Use% Mounted on
> ......
> /dev/sdd 1038336 32944 1005392 4% /nfs/pnfs
> /dev/sdc 10475520 32928 10442592 1% /nfs/xfs
> /dev/sde 999320 1284 929224 1% /nfs/test
> # mount -t nfs 127.0.0.1:/nfs/ /mnt
> # ll /mnt/*/
> /mnt/pnfs/:
> total 0
> -rw-r--r--. 1 root root 0 Apr 21 22:23 attr
> drwxr-xr-x. 2 root root 6 Apr 21 22:19 tmp
>
> /mnt/xfs/:
> total 0
> # umount /nfs/test/
> umount: /nfs/test/: target is busy
> (In some cases useful info about processes that
> use the device is found by lsof(8) or fuser(1).)
>
> I don't think that's user expect, they want umount /nfs/test/.
>
> It's caused by exports cache of nfsd holds the reference of
> the path (here is /nfs/test/), so, it can't be umounted.
>
> The patch site using fs_pin instead of mntget for export cache,
> user at nfs server can unmount any mount points includes exported
> for nfs. Maybe, only umounted for unexported mount points is better?
Thanks for this patch. It looks good!
My only comment on the code is that I would really like to see a
"path_get_pin()" and "path_put_unpin()" rather than open coding:
> + dget(item->ek_path.dentry);
> + pin_insert_group(&new->ek_pin, item->ek_path.mnt, NULL);
and
> + dput(key->ek_path.dentry);
> + pin_remove(&key->ek_pin);
But the question you raise is an important one: Exactly which filesystems
should be allowed to be unmounted?
This is a change in behaviour - is it one that people uniformly would want?
The kernel doesn't currently know which file systems were explicitly listed
in /etc/exports, and which were found by following a 'crossmnt'.
It could guess and allow the unmounting of anything below a 'crossmnt', but I
wouldn't be comfortable with that - it is error prone.
mountd does know what is in /etc/exports, and could tell the kernel.
For the expkey cache, we could always use path_get_pin.
For the export cache (where flags are available) we could use path_get
or path_get_pin depending on some new flag.
I'm not really sure it is worth it. I would rather the filesystems could
always be unmounted. But doing that could possibly break someone's work
flow. Maybe.
Or maybe I'm seeing problems where there aren't any.
Anyone else have an opinion?
Thanks,
NeilBrown
>
> Signed-off-by: Kinglong Mee <kinglongmee@xxxxxxxxx>
> ---
> fs/nfsd/export.c | 37 ++++++++++++++++++++++++++++++-------
> fs/nfsd/export.h | 10 +++++++++-
> 2 files changed, 39 insertions(+), 8 deletions(-)
>
> diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
> index f79521a..80f82f5 100644
> --- a/fs/nfsd/export.c
> +++ b/fs/nfsd/export.c
> @@ -42,10 +42,12 @@ static void expkey_put(struct kref *ref)
> struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
>
> if (test_bit(CACHE_VALID, &key->h.flags) &&
> - !test_bit(CACHE_NEGATIVE, &key->h.flags))
> - path_put(&key->ek_path);
> + !test_bit(CACHE_NEGATIVE, &key->h.flags)) {
> + dput(key->ek_path.dentry);
> + pin_remove(&key->ek_pin);
> + }
> auth_domain_put(key->ek_client);
> - kfree(key);
> + kfree_rcu(key, rcu_head);
> }
>
> static void expkey_request(struct cache_detail *cd,
> @@ -120,6 +122,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
> goto out;
>
> key.ek_client = dom;
> + key.cd = cd;
> key.ek_fsidtype = fsidtype;
> memcpy(key.ek_fsid, buf, len);
>
> @@ -210,6 +213,13 @@ static inline void expkey_init(struct cache_head *cnew,
> new->ek_fsidtype = item->ek_fsidtype;
>
> memcpy(new->ek_fsid, item->ek_fsid, sizeof(new->ek_fsid));
> + new->cd = item->cd;
> +}
> +
> +static void expkey_pin_kill(struct fs_pin *pin)
> +{
> + struct svc_expkey *key = container_of(pin, struct svc_expkey, ek_pin);
> + cache_force_expire(key->cd, &key->h);
> }
>
> static inline void expkey_update(struct cache_head *cnew,
> @@ -218,8 +228,10 @@ static inline void expkey_update(struct cache_head *cnew,
> struct svc_expkey *new = container_of(cnew, struct svc_expkey, h);
> struct svc_expkey *item = container_of(citem, struct svc_expkey, h);
>
> + init_fs_pin(&new->ek_pin, expkey_pin_kill);
> new->ek_path = item->ek_path;
> - path_get(&item->ek_path);
> + dget(item->ek_path.dentry);
> + pin_insert_group(&new->ek_pin, item->ek_path.mnt, NULL);
> }
>
> static struct cache_head *expkey_alloc(void)
> @@ -309,11 +321,13 @@ static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc)
> static void svc_export_put(struct kref *ref)
> {
> struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
> - path_put(&exp->ex_path);
> +
> + dput(exp->ex_path.dentry);
> + pin_remove(&exp->ex_pin);
> auth_domain_put(exp->ex_client);
> nfsd4_fslocs_free(&exp->ex_fslocs);
> kfree(exp->ex_uuid);
> - kfree(exp);
> + kfree_rcu(exp, rcu_head);
> }
>
> static void svc_export_request(struct cache_detail *cd,
> @@ -694,15 +708,23 @@ static int svc_export_match(struct cache_head *a, struct cache_head *b)
> path_equal(&orig->ex_path, &new->ex_path);
> }
>
> +static void export_pin_kill(struct fs_pin *pin)
> +{
> + struct svc_export *exp = container_of(pin, struct svc_export, ex_pin);
> + cache_force_expire(exp->cd, &exp->h);
> +}
> +
> static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
> {
> struct svc_export *new = container_of(cnew, struct svc_export, h);
> struct svc_export *item = container_of(citem, struct svc_export, h);
>
> + init_fs_pin(&new->ex_pin, export_pin_kill);
> kref_get(&item->ex_client->ref);
> new->ex_client = item->ex_client;
> new->ex_path = item->ex_path;
> - path_get(&item->ex_path);
> + dget(item->ex_path.dentry);
> + pin_insert_group(&new->ex_pin, item->ex_path.mnt, NULL);
> new->ex_fslocs.locations = NULL;
> new->ex_fslocs.locations_count = 0;
> new->ex_fslocs.migrated = 0;
> @@ -811,6 +833,7 @@ exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type,
>
> key.ek_client = clp;
> key.ek_fsidtype = fsid_type;
> + key.cd = cd;
> memcpy(key.ek_fsid, fsidv, key_len(fsid_type));
>
> ek = svc_expkey_lookup(cd, &key);
> diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
> index 1f52bfc..1cf6ada 100644
> --- a/fs/nfsd/export.h
> +++ b/fs/nfsd/export.h
> @@ -4,6 +4,7 @@
> #ifndef NFSD_EXPORT_H
> #define NFSD_EXPORT_H
>
> +#include <linux/fs_pin.h>
> #include <linux/sunrpc/cache.h>
> #include <uapi/linux/nfsd/export.h>
>
> @@ -46,6 +47,8 @@ struct exp_flavor_info {
>
> struct svc_export {
> struct cache_head h;
> + struct cache_detail *cd;
> +
> struct auth_domain * ex_client;
> int ex_flags;
> struct path ex_path;
> @@ -58,7 +61,9 @@ struct svc_export {
> struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST];
> enum pnfs_layouttype ex_layout_type;
> struct nfsd4_deviceid_map *ex_devid_map;
> - struct cache_detail *cd;
> +
> + struct fs_pin ex_pin;
> + struct rcu_head rcu_head;
> };
>
> /* an "export key" (expkey) maps a filehandlefragement to an
> @@ -67,12 +72,15 @@ struct svc_export {
> */
> struct svc_expkey {
> struct cache_head h;
> + struct cache_detail *cd;
>
> struct auth_domain * ek_client;
> int ek_fsidtype;
> u32 ek_fsid[6];
>
> struct path ek_path;
> + struct fs_pin ek_pin;
> + struct rcu_head rcu_head;
> };
>
> #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC))
Attachment:
pgpXb8Bg5XIE2.pgp
Description: OpenPGP digital signature
