From 502aa0a5be633e6558574ebcf63b65afdfbfcd7a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 10 Aug 2016 14:46:27 -0400 Subject: [PATCH 1/3] nfsd: fix dentry refcounting on create b44061d0b9 introduced a dentry ref counting bug. Previously we were grabbing one ref to dchild in nfsd_create(), but with the creation of nfsd_create_locked() we have a ref for dchild from the lookup in nfsd_create(), and then another ref in nfsd_create_locked(). The ref from the lookup in nfsd_create() is never dropped and results in dentries still in use at unmount. Signed-off-by: Josef Bacik Fixes: b44061d0b9 "nfsd: reorganize nfsd_create" Reported-by: kernel test robot Reviewed-by: Jeff Layton Acked-by: Al Viro Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ba944123167b..ff476e654b8f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1252,10 +1252,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dchild)) return nfserrno(host_err); err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) { - dput(dchild); + /* + * We unconditionally drop our ref to dchild as fh_compose will have + * already grabbed its own ref for it. + */ + dput(dchild); + if (err) return err; - } return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, rdev, resfhp); } From 42691398be08bd1fe99326911a0aa31f2c041d53 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 Aug 2016 10:37:30 -0400 Subject: [PATCH 2/3] nfsd: Fix race between FREE_STATEID and LOCK When running LTP's nfslock01 test, the Linux client can send a LOCK and a FREE_STATEID request at the same time. The outcome is: Frame 324 R OPEN stateid [2,O] Frame 115004 C LOCK lockowner_is_new stateid [2,O] offset 672000 len 64 Frame 115008 R LOCK stateid [1,L] Frame 115012 C WRITE stateid [0,L] offset 672000 len 64 Frame 115016 R WRITE NFS4_OK Frame 115019 C LOCKU stateid [1,L] offset 672000 len 64 Frame 115022 R LOCKU NFS4_OK Frame 115025 C FREE_STATEID stateid [2,L] Frame 115026 C LOCK lockowner_is_new stateid [2,O] offset 672128 len 64 Frame 115029 R FREE_STATEID NFS4_OK Frame 115030 R LOCK stateid [3,L] Frame 115034 C WRITE stateid [0,L] offset 672128 len 64 Frame 115038 R WRITE NFS4ERR_BAD_STATEID In other words, the server returns stateid L in a successful LOCK reply, but it has already released it. Subsequent uses of stateid L fail. To address this, protect the generation check in nfsd4_free_stateid with the st_mutex. This should guarantee that only one of two outcomes occurs: either LOCK returns a fresh valid stateid, or FREE_STATEID returns NFS4ERR_LOCKS_HELD. Reported-by: Alexey Kodanev Fix-suggested-by: Jeff Layton Signed-off-by: Chuck Lever Tested-by: Alexey Kodanev Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8410ca275db1..0edc1822f144 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4903,6 +4903,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } +static __be32 +nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) +{ + struct nfs4_ol_stateid *stp = openlockstateid(s); + __be32 ret; + + mutex_lock(&stp->st_mutex); + + ret = check_stateid_generation(stateid, &s->sc_stateid, 1); + if (ret) + goto out; + + ret = nfserr_locks_held; + if (check_for_locks(stp->st_stid.sc_file, + lockowner(stp->st_stateowner))) + goto out; + + release_lock_stateid(stp); + ret = nfs_ok; + +out: + mutex_unlock(&stp->st_mutex); + nfs4_put_stid(s); + return ret; +} + __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *free_stateid) @@ -4910,7 +4936,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_ol_stateid *stp; struct nfs4_client *cl = cstate->session->se_client; __be32 ret = nfserr_bad_stateid; @@ -4929,18 +4954,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ret = nfserr_locks_held; break; case NFS4_LOCK_STID: - ret = check_stateid_generation(stateid, &s->sc_stateid, 1); - if (ret) - break; - stp = openlockstateid(s); - ret = nfserr_locks_held; - if (check_for_locks(stp->st_stid.sc_file, - lockowner(stp->st_stateowner))) - break; - WARN_ON(!unhash_lock_stateid(stp)); + atomic_inc(&s->sc_count); spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; + ret = nfsd4_free_lock_stateid(stateid, s); goto out; case NFS4_REVOKED_DELEG_STID: dp = delegstateid(s); From dd257933fa4b9fea66a1195f8a15111029810abc Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 11 Aug 2016 10:37:39 -0400 Subject: [PATCH 3/3] nfsd: don't return an unhashed lock stateid after taking mutex nfsd4_lock will take the st_mutex before working with the stateid it gets, but between the time when we drop the cl_lock and take the mutex, the stateid could become unhashed (a'la FREE_STATEID). If that happens the lock stateid returned to the client will be forgotten. Fix this by first moving the st_mutex acquisition into lookup_or_create_lock_state. Then, have it check to see if the lock stateid is still hashed after taking the mutex. If it's not, then put the stateid and try the find/create again. Signed-off-by: Jeff Layton Tested-by: Alexey Kodanev Cc: stable@vger.kernel.org # feb9dad5 nfsd: Always lock state exclusively. Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 0edc1822f144..a204d7e109d4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5523,7 +5523,7 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, - struct nfs4_ol_stateid **lst, bool *new) + struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; @@ -5531,7 +5531,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; + struct nfs4_ol_stateid *lst; unsigned int strhashval; + bool hashed; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { @@ -5547,12 +5549,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, goto out; } - *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); - if (*lst == NULL) { +retry: + lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); + if (lst == NULL) { status = nfserr_jukebox; goto out; } + + mutex_lock(&lst->st_mutex); + + /* See if it's still hashed to avoid race with FREE_STATEID */ + spin_lock(&cl->cl_lock); + hashed = !list_empty(&lst->st_perfile); + spin_unlock(&cl->cl_lock); + + if (!hashed) { + mutex_unlock(&lst->st_mutex); + nfs4_put_stid(&lst->st_stid); + goto retry; + } status = nfs_ok; + *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; @@ -5619,8 +5636,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); - if (status == nfs_ok) - mutex_lock(&lock_stp->st_mutex); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid,