On Wed, 2023-01-18 at 21:05 -0800, dai.ngo@xxxxxxxxxx wrote:
> On 1/17/23 11:38 AM, Jeff Layton wrote:
> > There are two different flavors of the nfsd4_copy struct. One is
> > embedded in the compound and is used directly in synchronous copies. The
> > other is dynamically allocated, refcounted and tracked in the client
> > struture. For the embedded one, the cleanup just involves releasing any
> > nfsd_files held on its behalf. For the async one, the cleanup is a bit
> > more involved, and we need to dequeue it from lists, unhash it, etc.
> >
> > There is at least one potential refcount leak in this code now. If the
> > kthread_create call fails, then both the src and dst nfsd_files in the
> > original nfsd4_copy object are leaked.
> >
> > The cleanup in this codepath is also sort of weird. In the async copy
> > case, we'll have up to four nfsd_file references (src and dst for both
> > flavors of copy structure). They are both put at the end of
> > nfsd4_do_async_copy, even though the ones held on behalf of the embedded
> > one outlive that structure.
> >
> > Change it so that we always clean up the nfsd_file refs held by the
> > embedded copy structure before nfsd4_copy returns. Rework
> > cleanup_async_copy to handle both inter and intra copies. Eliminate
> > nfsd4_cleanup_intra_ssc since it now becomes a no-op.
> >
> > Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
> > ---
> > fs/nfsd/nfs4proc.c | 23 ++++++++++-------------
> > 1 file changed, 10 insertions(+), 13 deletions(-)
> >
> > diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
> > index 37a9cc8ae7ae..62b9d6c1b18b 100644
> > --- a/fs/nfsd/nfs4proc.c
> > +++ b/fs/nfsd/nfs4proc.c
> > @@ -1512,7 +1512,6 @@ nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp,
> > long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout);
> >
> > nfs42_ssc_close(filp);
> > - nfsd_file_put(dst);
>
> I think we still need this, in addition to release_copy_files called
> from cleanup_async_copy. For async inter-copy, there are 2 reference
> count added to the destination file, one from nfsd4_setup_inter_ssc
> and the other one from dup_copy_fields. The above nfsd_file_put is for
> the count added by dup_copy_fields.
>
With this patch, the references held by the original copy structure are
put by the call to release_copy_files at the end of nfsd4_copy. That
means that the kthread task is only responsible for putting the
references held by the (kmalloc'ed) async_copy structure. So, I think
this gets the nfsd_file refcounting right.
> > fput(filp);
> >
> > spin_lock(&nn->nfsd_ssc_lock);
> > @@ -1562,13 +1561,6 @@ nfsd4_setup_intra_ssc(struct svc_rqst *rqstp,
> > ©->nf_dst);
> > }
> >
> > -static void
> > -nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst)
> > -{
> > - nfsd_file_put(src);
> > - nfsd_file_put(dst);
> > -}
> > -
> > static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
> > {
> > struct nfsd4_cb_offload *cbo =
> > @@ -1683,12 +1675,18 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
> > dst->ss_nsui = src->ss_nsui;
> > }
> >
> > +static void release_copy_files(struct nfsd4_copy *copy)
> > +{
> > + if (copy->nf_src)
> > + nfsd_file_put(copy->nf_src);
> > + if (copy->nf_dst)
> > + nfsd_file_put(copy->nf_dst);
> > +}
> > +
> > static void cleanup_async_copy(struct nfsd4_copy *copy)
> > {
> > nfs4_free_copy_state(copy);
> > - nfsd_file_put(copy->nf_dst);
> > - if (!nfsd4_ssc_is_inter(copy))
> > - nfsd_file_put(copy->nf_src);
> > + release_copy_files(copy);
> > spin_lock(©->cp_clp->async_lock);
> > list_del(©->copies);
> > spin_unlock(©->cp_clp->async_lock);
> > @@ -1748,7 +1746,6 @@ static int nfsd4_do_async_copy(void *data)
> > } else {
> > nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file,
> > copy->nf_dst->nf_file, false);
> > - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
> > }
> >
> > do_callback:
> > @@ -1811,9 +1808,9 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> > } else {
> > status = nfsd4_do_copy(copy, copy->nf_src->nf_file,
> > copy->nf_dst->nf_file, true);
> > - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
> > }
> > out:
> > + release_copy_files(copy);
> > return status;
> > out_err:
>
> This is unrelated to the reference count issue.
>
> Here if this is an inter-copy then we need to decrement the reference
> count of the nfsd4_ssc_umount_item so that the vfsmount can be unmounted
> later.
>
Oh, I think I see what you mean. Maybe something like the (untested)
patch below on top of the original patch would fix that?
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index c9057462b973..7475c593553c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1511,8 +1511,10 @@ nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp,
struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id);
long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout);
- nfs42_ssc_close(filp);
- fput(filp);
+ if (filp) {
+ nfs42_ssc_close(filp);
+ fput(filp);
+ }
spin_lock(&nn->nfsd_ssc_lo
list_del(&nsui->nsui_list);
@@ -1813,8 +1815,13 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
release_copy_files(copy);
return status;
out_err:
- if (async_copy)
+ if (async_copy) {
cleanup_async_copy(async_copy);
+ if (nfsd4_ssc_is_inter(async_copy))
+ nfsd4_cleanup_inter_ssc(copy->ss_nsui, NULL,
+ copy->nf_dst);
+
+ }
status = nfserrno(-ENOMEM);
/*
* source's vfsmount of inter-copy will be unmounted
--
Jeff Layton <jlayton@xxxxxxxxxx>
