Re: [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg

["J. Bruce Fields" <bfields@fieldses.org>]

On Mon, Jun 30, 2014 at 11:48:33AM -0400, Jeff Layton wrote:
> state_lock is a heavily contended global lock. We don't want to grab
> that while simultaneously holding the inode->i_lock.
> 
> Add a new per-nfs4_file lock that we can use to protect the
> per-nfs4_file delegation list. Hold that while walking the list in the
> break_deleg callback and queue the workqueue job for each one.
> 
> The workqueue job can then take the state_lock and do the list
> manipulations without the i_lock being held prior to starting the
> rpc call.

The code tends to assume that the callback thread only works with the
delegation struct itself and puts it when done but doesn't otherwise
touch other state.

I wonder how this interacts with state shutdown.... 

E.g. in nfs4_state_shutdown_net() we walk the dl_recall_lru and destroy
everything we find, but this callback workqueue is still running so I
think another delegation could get added to that list after this?  Does
that cause bugs?

And it'd also be worth checking delegreturn and destroy_client.

Maybe there's no bug, or they just need to flush the workqueue at the
appropriate point.

There's also a preexisting expire_client/laundromat vs break race:

	- expire_client/laundromat adds a delegation to its local
	  reaplist using the same dl_recall_lru field that a delegation
	  uses to track its position on the recall lru and drops the
	  state lock.

	- a concurrent break_lease adds the delegation to the lru.

	- expire/client/laundromat then walks it reaplist and sees the
	  lru head as just another delegation on the list....

Possibly unrelated, but it might be good to fix that first.

--b.

> 
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
>  fs/nfsd/nfs4callback.c | 28 +++++++++++++++++++++-------
>  fs/nfsd/nfs4state.c    | 43 ++++++++++++++++++++++++++++---------------
>  fs/nfsd/state.h        |  2 ++
>  3 files changed, 51 insertions(+), 22 deletions(-)
> 
> diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
> index 00cb9b7a75f6..cba4ca375f5e 100644
> --- a/fs/nfsd/nfs4callback.c
> +++ b/fs/nfsd/nfs4callback.c
> @@ -43,7 +43,7 @@
>  #define NFSDDBG_FACILITY                NFSDDBG_PROC
>  
>  static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
> -static void nfsd4_do_callback_rpc(struct work_struct *w);
> +static void nfsd4_run_cb_null(struct work_struct *w);
>  
>  #define NFSPROC4_CB_NULL 0
>  #define NFSPROC4_CB_COMPOUND 1
> @@ -764,7 +764,7 @@ static void do_probe_callback(struct nfs4_client *clp)
>  
>  	cb->cb_ops = &nfsd4_cb_probe_ops;
>  
> -	INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> +	INIT_WORK(&cb->cb_work, nfsd4_run_cb_null);
>  
>  	run_nfsd4_cb(cb);
>  }
> @@ -936,7 +936,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
>  	set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
>  	/*
>  	 * Note this won't actually result in a null callback;
> -	 * instead, nfsd4_do_callback_rpc() will detect the killed
> +	 * instead, nfsd4_run_cb_null() will detect the killed
>  	 * client, destroy the rpc client, and stop:
>  	 */
>  	do_probe_callback(clp);
> @@ -1014,9 +1014,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
>  		run_nfsd4_cb(cb);
>  }
>  
> -static void nfsd4_do_callback_rpc(struct work_struct *w)
> +static void nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
>  {
> -	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
>  	struct nfs4_client *clp = cb->cb_clp;
>  	struct rpc_clnt *clnt;
>  
> @@ -1034,6 +1033,22 @@ static void nfsd4_do_callback_rpc(struct work_struct *w)
>  			cb->cb_ops, cb);
>  }
>  
> +static void nfsd4_run_cb_null(struct work_struct *w)
> +{
> +	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> +							cb_work);
> +	nfsd4_run_callback_rpc(cb);
> +}
> +
> +static void nfsd4_run_cb_recall(struct work_struct *w)
> +{
> +	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> +							cb_work);
> +
> +	nfsd4_prepare_cb_recall(cb->cb_op);
> +	nfsd4_run_callback_rpc(cb);
> +}
> +
>  void nfsd4_cb_recall(struct nfs4_delegation *dp)
>  {
>  	struct nfsd4_callback *cb = &dp->dl_recall;
> @@ -1050,8 +1065,7 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
>  
>  	INIT_LIST_HEAD(&cb->cb_per_client);
>  	cb->cb_done = true;
> -
> -	INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> +	INIT_WORK(&cb->cb_work, nfsd4_run_cb_recall);
>  
>  	run_nfsd4_cb(&dp->dl_recall);
>  }
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index b49b46b0ce23..461229a01963 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -513,7 +513,9 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
>  	lockdep_assert_held(&state_lock);
>  
>  	dp->dl_stid.sc_type = NFS4_DELEG_STID;
> +	spin_lock(&fp->fi_lock);
>  	list_add(&dp->dl_perfile, &fp->fi_delegations);
> +	spin_unlock(&fp->fi_lock);
>  	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
>  }
>  
> @@ -521,14 +523,18 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
>  static void
>  unhash_delegation(struct nfs4_delegation *dp)
>  {
> +	struct nfs4_file *fp = dp->dl_file;
> +
>  	spin_lock(&state_lock);
>  	list_del_init(&dp->dl_perclnt);
> -	list_del_init(&dp->dl_perfile);
>  	list_del_init(&dp->dl_recall_lru);
> +	spin_lock(&fp->fi_lock);
> +	list_del_init(&dp->dl_perfile);
> +	spin_unlock(&fp->fi_lock);
>  	spin_unlock(&state_lock);
> -	if (dp->dl_file) {
> -		nfs4_put_deleg_lease(dp->dl_file);
> -		put_nfs4_file(dp->dl_file);
> +	if (fp) {
> +		nfs4_put_deleg_lease(fp);
> +		put_nfs4_file(fp);
>  		dp->dl_file = NULL;
>  	}
>  }
> @@ -2612,6 +2618,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
>  	lockdep_assert_held(&state_lock);
>  
>  	atomic_set(&fp->fi_ref, 1);
> +	spin_lock_init(&fp->fi_lock);
>  	INIT_LIST_HEAD(&fp->fi_stateids);
>  	INIT_LIST_HEAD(&fp->fi_delegations);
>  	ihold(ino);
> @@ -2857,26 +2864,32 @@ out:
>  	return ret;
>  }
>  
> -static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> +void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
>  {
>  	struct nfs4_client *clp = dp->dl_stid.sc_client;
>  	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
>  
> -	lockdep_assert_held(&state_lock);
> +	/*
> +	 * We can't do this in nfsd_break_deleg_cb because it is
> +	 * already holding inode->i_lock
> +	 */
> +	spin_lock(&state_lock);
> +	if (list_empty(&dp->dl_recall_lru)) {
> +		dp->dl_time = get_seconds();
> +		list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> +	}
> +	spin_unlock(&state_lock);
> +}
> +
> +static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> +{
>  	/* We're assuming the state code never drops its reference
>  	 * without first removing the lease.  Since we're in this lease
>  	 * callback (and since the lease code is serialized by the kernel
>  	 * lock) we know the server hasn't removed the lease yet, we know
>  	 * it's safe to take a reference: */
>  	atomic_inc(&dp->dl_count);
> -
> -	list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> -
> -	/* Only place dl_time is set; protected by i_lock: */
> -	dp->dl_time = get_seconds();
> -
>  	block_delegations(&dp->dl_fh);
> -
>  	nfsd4_cb_recall(dp);
>  }
>  
> @@ -2901,11 +2914,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
>  	 */
>  	fl->fl_break_time = 0;
>  
> -	spin_lock(&state_lock);
>  	fp->fi_had_conflict = true;
> +	spin_lock(&fp->fi_lock);
>  	list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
>  		nfsd_break_one_deleg(dp);
> -	spin_unlock(&state_lock);
> +	spin_unlock(&fp->fi_lock);
>  }
>  
>  static
> diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
> index 9447f86f2778..7d6ba06c1abe 100644
> --- a/fs/nfsd/state.h
> +++ b/fs/nfsd/state.h
> @@ -382,6 +382,7 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
>  /* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
>  struct nfs4_file {
>  	atomic_t		fi_ref;
> +	spinlock_t		fi_lock;
>  	struct hlist_node       fi_hash;    /* hash by "struct inode *" */
>  	struct list_head        fi_stateids;
>  	struct list_head	fi_delegations;
> @@ -471,6 +472,7 @@ extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
>  extern int nfsd4_create_callback_queue(void);
>  extern void nfsd4_destroy_callback_queue(void);
>  extern void nfsd4_shutdown_callback(struct nfs4_client *);
> +extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
>  extern void nfs4_put_delegation(struct nfs4_delegation *dp);
>  extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
>  							struct nfsd_net *nn);
> -- 
> 1.9.3
>