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.
/nfs/xfs *(rw,insecure,no_subtree_check,no_root_squash)
/nfs/pnfs *(rw,insecure,no_subtree_check,no_root_squash)
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
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
/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/: 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.
v2,
1. Update exports according to the "allow_umount" option.
Pin to vfsmnt default, change when updating.
2. Using kzalloc for all memory allocating without kmalloc.
Signed-off-by: Kinglong Mee <kinglongmee@xxxxxxxxx>
---
fs/nfsd/export.c | 52 ++++++++++++++++++++++++++++++++--------
fs/nfsd/export.h | 11 ++++++++-
include/uapi/linux/nfsd/export.h | 3 ++-
3 files changed, 54 insertions(+), 12 deletions(-)
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index f79521a..cc34b0b 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -43,9 +43,9 @@ static void expkey_put(struct kref *ref)
if (test_bit(CACHE_VALID, &key->h.flags) &&
!test_bit(CACHE_NEGATIVE, &key->h.flags))
- path_put(&key->ek_path);
+ path_put_unpin(&key->ek_path, &key->ek_pin);
auth_domain_put(key->ek_client);
- kfree(key);
+ kfree_rcu(key, rcu_head);
}
static void expkey_request(struct cache_detail *cd,
@@ -83,7 +83,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
return -EINVAL;
mesg[mlen-1] = 0;
- buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
err = -ENOMEM;
if (!buf)
goto out;
@@ -120,6 +120,7 @@ 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 +211,13 @@ 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,
@@ -218,13 +226,14 @@ 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);
+ path_get_pin(&new->ek_path, &new->ek_pin);
}
static struct cache_head *expkey_alloc(void)
{
- struct svc_expkey *i = kmalloc(sizeof(*i), GFP_KERNEL);
+ struct svc_expkey *i = kzalloc(sizeof(*i), GFP_KERNEL);
if (i)
return &i->h;
else
@@ -309,11 +318,16 @@ 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);
+
+ if (EX_ALLOW_UMOUNT(exp))
+ path_put_unpin(&exp->ex_path, &exp->ex_pin);
+ else
+ path_put(&exp->ex_path);
+
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,
@@ -520,7 +534,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
return -EINVAL;
mesg[mlen-1] = 0;
- buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -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_flags = NFSEXP_ALLOW_UMOUNT;
new->ex_client = item->ex_client;
new->ex_path = item->ex_path;
- path_get(&item->ex_path);
+ path_get_pin(&new->ex_path, &new->ex_pin);
new->ex_fslocs.locations = NULL;
new->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = 0;
@@ -717,6 +739,14 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
struct svc_export *item = container_of(citem, struct svc_export, h);
int i;
+ if (!EX_ALLOW_UMOUNT(item)) {
+ path_get(&new->ex_path);
+ if (EX_ALLOW_UMOUNT(new))
+ path_put_unpin(&new->ex_path, &new->ex_pin);
+ else
+ path_put(&new->ex_path);
+ }
+
new->ex_flags = item->ex_flags;
new->ex_anon_uid = item->ex_anon_uid;
new->ex_anon_gid = item->ex_anon_gid;
@@ -740,7 +770,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
static struct cache_head *svc_export_alloc(void)
{
- struct svc_export *i = kmalloc(sizeof(*i), GFP_KERNEL);
+ struct svc_export *i = kzalloc(sizeof(*i), GFP_KERNEL);
if (i)
return &i->h;
else
@@ -811,6 +841,7 @@ 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);
@@ -1159,6 +1190,7 @@ static struct flags {
{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
{ NFSEXP_V4ROOT, {"v4root", ""}},
{ NFSEXP_PNFS, {"pnfs", ""}},
+ { NFSEXP_ALLOW_UMOUNT, {"allow_umount", ""}},
{ 0, {"", ""}}
};
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 1f52bfc..1134875 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
@@ -67,17 +72,21 @@ 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))
#define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE)
#define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
+#define EX_ALLOW_UMOUNT(exp) ((exp)->ex_flags & NFSEXP_ALLOW_UMOUNT)
int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp);
__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp);
diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h
index 0df7bd5..61aa8bb 100644
--- a/include/uapi/linux/nfsd/export.h
+++ b/include/uapi/linux/nfsd/export.h
@@ -51,9 +51,10 @@
*/
#define NFSEXP_V4ROOT 0x10000
#define NFSEXP_PNFS 0x20000
+#define NFSEXP_ALLOW_UMOUNT 0x40000
/* All flags that we claim to support. (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS 0x3FE7F
+#define NFSEXP_ALLFLAGS 0x7FE7F
/* The flags that may vary depending on security flavor: */
#define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
--
2.4.1
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
