On Wed, 2024-08-28 at 21:04 -0400, Mike Snitzer wrote:
> Introduce nfsd_serv_try_get and nfsd_serv_put and update the nfsd code
> to prevent nfsd_destroy_serv from destroying nn->nfsd_serv until any
> caller of nfsd_serv_try_get releases their reference using nfsd_serv_put.
>
> A percpu_ref is used to implement the interlock between
> nfsd_destroy_serv and any caller of nfsd_serv_try_get.
>
> This interlock is needed to properly wait for the completion of client
> initiated localio calls to nfsd (that are _not_ in the context of nfsd).
>
> Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
> ---
> fs/nfsd/netns.h | 8 +++++++-
> fs/nfsd/nfssvc.c | 39 +++++++++++++++++++++++++++++++++++++++
> 2 files changed, 46 insertions(+), 1 deletion(-)
>
> diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
> index 238fc4e56e53..e2d953f21dde 100644
> --- a/fs/nfsd/netns.h
> +++ b/fs/nfsd/netns.h
> @@ -13,6 +13,7 @@
> #include <linux/filelock.h>
> #include <linux/nfs4.h>
> #include <linux/percpu_counter.h>
> +#include <linux/percpu-refcount.h>
> #include <linux/siphash.h>
> #include <linux/sunrpc/stats.h>
>
> @@ -139,7 +140,9 @@ struct nfsd_net {
>
> struct svc_info nfsd_info;
> #define nfsd_serv nfsd_info.serv
> -
> + struct percpu_ref nfsd_serv_ref;
> + struct completion nfsd_serv_confirm_done;
> + struct completion nfsd_serv_free_done;
>
> /*
> * clientid and stateid data for construction of net unique COPY
> @@ -221,6 +224,9 @@ struct nfsd_net {
> extern bool nfsd_support_version(int vers);
> extern unsigned int nfsd_net_id;
>
> +bool nfsd_serv_try_get(struct nfsd_net *nn);
> +void nfsd_serv_put(struct nfsd_net *nn);
> +
> void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
> void nfsd_reset_write_verifier(struct nfsd_net *nn);
> #endif /* __NFSD_NETNS_H__ */
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index defc430f912f..e43d440f9f0a 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -193,6 +193,30 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
> return 0;
> }
>
> +bool nfsd_serv_try_get(struct nfsd_net *nn)
> +{
> + return percpu_ref_tryget_live(&nn->nfsd_serv_ref);
> +}
> +
> +void nfsd_serv_put(struct nfsd_net *nn)
> +{
> + percpu_ref_put(&nn->nfsd_serv_ref);
> +}
> +
> +static void nfsd_serv_done(struct percpu_ref *ref)
> +{
> + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
> +
> + complete(&nn->nfsd_serv_confirm_done);
> +}
> +
> +static void nfsd_serv_free(struct percpu_ref *ref)
> +{
> + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
> +
> + complete(&nn->nfsd_serv_free_done);
> +}
> +
> /*
> * Maximum number of nfsd processes
> */
> @@ -392,6 +416,7 @@ static void nfsd_shutdown_net(struct net *net)
> lockd_down(net);
> nn->lockd_up = false;
> }
> + percpu_ref_exit(&nn->nfsd_serv_ref);
> nn->nfsd_net_up = false;
> nfsd_shutdown_generic();
> }
> @@ -471,6 +496,13 @@ void nfsd_destroy_serv(struct net *net)
> struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> struct svc_serv *serv = nn->nfsd_serv;
>
> + lockdep_assert_held(&nfsd_mutex);
> +
> + percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done);
> + wait_for_completion(&nn->nfsd_serv_confirm_done);
> + wait_for_completion(&nn->nfsd_serv_free_done);
> + /* percpu_ref_exit is called in nfsd_shutdown_net */
> +
> spin_lock(&nfsd_notifier_lock);
> nn->nfsd_serv = NULL;
> spin_unlock(&nfsd_notifier_lock);
> @@ -595,6 +627,13 @@ int nfsd_create_serv(struct net *net)
> if (nn->nfsd_serv)
> return 0;
>
> + error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free,
> + 0, GFP_KERNEL);
> + if (error)
> + return error;
> + init_completion(&nn->nfsd_serv_free_done);
> + init_completion(&nn->nfsd_serv_confirm_done);
> +
> if (nfsd_max_blksize == 0)
> nfsd_max_blksize = nfsd_get_default_max_blksize();
> nfsd_reset_versions(nn);
A little hard to review this one at this point in the series, as there
are no callers of get/put yet, but the concept seems reasonable.
Reviewed-by: Jeff Layton <jlayton@xxxxxxxxxx>
