Re: [PATCH v5 5/5] sunrpc: derive the pool count instead of caching it in sv_nrpools

On Tue, 2026-07-07 at 08:50 +1000, NeilBrown wrote:
> On Mon, 06 Jul 2026, Jeff Layton wrote:
> > Now that the pool mode is always pernode, svc_serv.sv_nrpools is
> > redundant with sv_is_pooled: an unpooled service always has a single
> > pool, and a pooled service has svc_pool_map.npools pools (which is one on
> > a single-node host). sv_nrpools cannot distinguish an unpooled service
> > from a pooled service that happens to have one pool, so it is sv_nrpools,
> > not sv_is_pooled, that carries no unique information.
> > 
> > Replace the cached field with a svc_serv_nrpools() helper that derives
> > the count from sv_is_pooled and the pool map, and convert all readers to
> > it. svc_pool_map is file-local to svc.c, so export the helper for the
> > svc_xprt.c and nfsd callers.
> > 
> > Reading svc_pool_map.npools without svc_pool_map_mutex is safe: the
> > mutex protects only svc_pool_map.count, and npools is already read
> > locklessly in svc_pool_for_cpu().
> > 
> > A pooled service holds a map reference for its whole lifetime, so npools
> > is stable while any reader could observe it.  The hot path
> > (svc_pool_for_cpu()) already dereferences svc_pool_map for to_pool, and
> > npools shares that cacheline, so there is no new locking or coherence
> > cost.
> > 
> > __svc_create() keeps using its local npools argument for the sv_pools[]
> > allocation, since sv_is_pooled is not set until svc_create_pooled() has
> > returned from it.
> > 
> > Doing this also removes a modulus operation from svc_pool_for_cpu(),
> > which should make for more efficient RPC queueing.
> > 
> > Assisted-by: Claude:claude-opus-4-8
> > Suggested-by: NeilBrown <[email protected]>
> > Signed-off-by: Jeff Layton <[email protected]>
> > ---
> >  fs/nfsd/nfsctl.c           |  2 +-
> >  fs/nfsd/nfssvc.c           | 10 ++++-----
> >  include/linux/sunrpc/svc.h |  2 +-
> >  net/sunrpc/svc.c           | 52 ++++++++++++++++++++++++++++++++--------------
> >  net/sunrpc/svc_xprt.c      |  6 +++---
> >  5 files changed, 46 insertions(+), 26 deletions(-)
> > 
> > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
> > index bc16fc7ca24f..0543e5bb842f 100644
> > --- a/fs/nfsd/nfsctl.c
> > +++ b/fs/nfsd/nfsctl.c
> > @@ -1526,7 +1526,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> >  
> >  	rcu_read_lock();
> >  
> > -	for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
> > +	for (i = 0; i < svc_serv_nrpools(nn->nfsd_serv); i++) {
> >  		struct svc_rqst *rqstp;
> >  		long thread_skip = 0;
> >  
> > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> > index a8ea4dbfa56b..2edf716ea022 100644
> > --- a/fs/nfsd/nfssvc.c
> > +++ b/fs/nfsd/nfssvc.c
> > @@ -655,7 +655,7 @@ int nfsd_nrpools(struct net *net)
> >  	if (nn->nfsd_serv == NULL)
> >  		return 0;
> >  	else
> > -		return nn->nfsd_serv->sv_nrpools;
> > +		return svc_serv_nrpools(nn->nfsd_serv);
> >  }
> >  
> >  int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
> > @@ -665,7 +665,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
> >  	int i;
> >  
> >  	if (serv)
> > -		for (i = 0; i < serv->sv_nrpools && i < n; i++)
> > +		for (i = 0; i < svc_serv_nrpools(serv) && i < n; i++)
> >  			nthreads[i] = serv->sv_pools[i].sp_nrthrmax;
> >  	return 0;
> >  }
> > @@ -699,8 +699,8 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
> >  	if (n == 1)
> >  		return svc_set_num_threads(nn->nfsd_serv, nn->min_threads, nthreads[0]);
> >  
> > -	if (n > nn->nfsd_serv->sv_nrpools)
> > -		n = nn->nfsd_serv->sv_nrpools;
> > +	if (n > svc_serv_nrpools(nn->nfsd_serv))
> > +		n = svc_serv_nrpools(nn->nfsd_serv);
> >  
> >  	/* enforce a global maximum number of threads */
> >  	tot = 0;
> > @@ -731,7 +731,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
> >  	}
> >  
> >  	/* Anything undefined in array is considered to be 0 */
> > -	for (i = n; i < nn->nfsd_serv->sv_nrpools; ++i) {
> > +	for (i = n; i < svc_serv_nrpools(nn->nfsd_serv); ++i) {
> >  		err = svc_set_pool_threads(nn->nfsd_serv,
> >  					   &nn->nfsd_serv->sv_pools[i],
> >  					   0, 0);
> > diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
> > index 3a0152d926fb..3c885ab6ad41 100644
> > --- a/include/linux/sunrpc/svc.h
> > +++ b/include/linux/sunrpc/svc.h
> > @@ -85,7 +85,6 @@ struct svc_serv {
> >  
> >  	char *			sv_name;	/* service name */
> >  
> > -	unsigned int		sv_nrpools;	/* number of thread pools */
> >  	bool			sv_is_pooled;	/* is this a pooled service? */
> >  	struct svc_pool *	sv_pools;	/* array of thread pools */
> >  	int			(*sv_threadfn)(void *data);
> > @@ -480,6 +479,7 @@ void		   svc_wake_up(struct svc_serv *);
> >  void		   svc_reserve(struct svc_rqst *rqstp, int space);
> >  void		   svc_pool_wake_idle_thread(struct svc_pool *pool);
> >  struct svc_pool   *svc_pool_for_cpu(struct svc_serv *serv);
> > +unsigned int	   svc_serv_nrpools(const struct svc_serv *serv);
> >  char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
> >  const char *	   svc_proc_name(const struct svc_rqst *rqstp);
> >  int		   svc_encode_result_payload(struct svc_rqst *rqstp,
> > diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
> > index ece69cb0138a..800514a14f17 100644
> > --- a/net/sunrpc/svc.c
> > +++ b/net/sunrpc/svc.c
> > @@ -224,7 +224,7 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
> >  	unsigned int node = m->pool_to[pidx];
> >  
> >  	/*
> > -	 * The caller checks for sv_nrpools > 1, which
> > +	 * The caller checks for more than one pool, which
> >  	 * implies that we've been initialized.
> >  	 */
> >  	WARN_ON_ONCE(m->count == 0);
> > @@ -234,6 +234,24 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
> >  	set_cpus_allowed_ptr(task, cpumask_of_node(node));
> >  }
> >  
> > +/**
> > + * svc_serv_nrpools - number of thread pools backing a service
> > + * @serv: An RPC service
> > + *
> > + * Pooled services all share the global svc_pool_map, so their pool count
> > + * is svc_pool_map.npools. Unpooled services have a single pool. Reading
> > + * npools without svc_pool_map_mutex is safe: a pooled service holds a map
> > + * reference for its whole lifetime, so npools is stable once set.
> > + *
> > + * Return value:
> > + *   The number of pools in @serv
> > + */
> > +unsigned int svc_serv_nrpools(const struct svc_serv *serv)
> > +{
> > +	return serv->sv_is_pooled ? svc_pool_map.npools : 1;
> > +}
> > +EXPORT_SYMBOL_GPL(svc_serv_nrpools);
> 
> I would make this a static-inline.
> 

That would mean that we would have to export svc_pool_map, which is
currently private to svc.c.

> > +
> >  /**
> >   * svc_pool_for_cpu - Select pool to run a thread on this cpu
> >   * @serv: An RPC service
> > @@ -247,12 +265,15 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
> >  struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv)
> >  {
> >  	struct svc_pool_map *m = &svc_pool_map;
> > +	unsigned int nrpools = svc_serv_nrpools(serv);
> >  	unsigned int pidx, i;
> >  
> > -	if (serv->sv_nrpools <= 1)
> > +	if (nrpools <= 1)
> >  		return serv->sv_pools;
> >  
> > -	pidx = m->to_pool[cpu_to_node(raw_smp_processor_id())] % serv->sv_nrpools;
> > +	pidx = m->to_pool[cpu_to_node(raw_smp_processor_id())];
> > +	if (pidx >= nrpools)
> > +		pidx = 0;
> 
> The values stored in svc_pool_map.to_pool are all less than
> svc_pool_map.npools.
> So that if() condition cannot be true. 
> 
> But those two things don't reduce the correctness of the patch.
> 
> Reviewed-by: NeilBrown <[email protected]>
> 
> Thanks for doing this.
> NeilBrown
> 

Ahh good point. I guess we can remove that if statement. I can send
Chuck a follow-on patch. Thanks for the R-b!

> 
> >  
> >  	/*
> >  	 * It's possible to have a pool with no threads. Userland can just set
> > @@ -265,7 +286,7 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv)
> >  	 * populated pool, trading NUMA locality for a guarantee that the
> >  	 * transport is serviced.
> >  	 */
> > -	for (i = 0; i < serv->sv_nrpools; i++) {
> > +	for (i = 0; i < nrpools; i++) {
> >  		struct svc_pool *pool = &serv->sv_pools[pidx];
> >  
> >  		/* This is set under the sp_mutex and rarely ever changes. A
> > @@ -274,7 +295,7 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv)
> >  		if (data_race(pool->sp_nrthreads))
> >  			return pool;
> >  
> > -		if (++pidx >= serv->sv_nrpools)
> > +		if (++pidx >= nrpools)
> >  			pidx = 0;
> >  	}
> >  
> > @@ -414,15 +435,13 @@ __svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats,
> >  
> >  	__svc_init_bc(serv);
> >  
> > -	serv->sv_nrpools = npools;
> > -	serv->sv_pools =
> > -		kzalloc_objs(struct svc_pool, serv->sv_nrpools);
> > +	serv->sv_pools = kzalloc_objs(struct svc_pool, npools);
> >  	if (!serv->sv_pools) {
> >  		kfree(serv);
> >  		return NULL;
> >  	}
> >  
> > -	for (i = 0; i < serv->sv_nrpools; i++) {
> > +	for (i = 0; i < npools; i++) {
> >  		struct svc_pool *pool = &serv->sv_pools[i];
> >  
> >  		dprintk("svc: initialising pool %u for %s\n",
> > @@ -520,7 +539,7 @@ svc_destroy(struct svc_serv **servp)
> >  
> >  	cache_clean_deferred(serv);
> >  
> > -	for (i = 0; i < serv->sv_nrpools; i++) {
> > +	for (i = 0; i < svc_serv_nrpools(serv); i++) {
> >  		struct svc_pool *pool = &serv->sv_pools[i];
> >  
> >  		svc_pool_destroy_counters(pool);
> > @@ -732,7 +751,7 @@ int svc_new_thread(struct svc_serv *serv, struct svc_pool *pool)
> >  	}
> >  
> >  	rqstp->rq_task = task;
> > -	if (serv->sv_nrpools > 1)
> > +	if (svc_serv_nrpools(serv) > 1)
> >  		svc_pool_map_set_cpumask(task, pool->sp_id);
> >  
> >  	svc_sock_update_bufs(serv);
> > @@ -858,8 +877,9 @@ int
> >  svc_set_num_threads(struct svc_serv *serv, unsigned int min_threads,
> >  		    unsigned int nrservs)
> >  {
> > -	unsigned int base = nrservs / serv->sv_nrpools;
> > -	unsigned int remain = nrservs % serv->sv_nrpools;
> > +	unsigned int nrpools = svc_serv_nrpools(serv);
> > +	unsigned int base = nrservs / nrpools;
> > +	unsigned int remain = nrservs % nrpools;
> >  	int i, err = 0;
> >  
> >  	/*
> > @@ -870,9 +890,9 @@ svc_set_num_threads(struct svc_serv *serv, unsigned int min_threads,
> >  	 * @nrservs.
> >  	 */
> >  	if (base == 0 && nrservs != 0)
> > -		remain = serv->sv_nrpools;
> > +		remain = nrpools;
> >  
> > -	for (i = 0; i < serv->sv_nrpools; ++i) {
> > +	for (i = 0; i < nrpools; ++i) {
> >  		struct svc_pool *pool = &serv->sv_pools[i];
> >  		int threads = base;
> >  
> > @@ -906,7 +926,7 @@ unsigned int svc_serv_maxthreads(const struct svc_serv *serv)
> >  {
> >  	unsigned int i, max = 0;
> >  
> > -	for (i = 0; i < serv->sv_nrpools; i++)
> > +	for (i = 0; i < svc_serv_nrpools(serv); i++)
> >  		max += data_race(serv->sv_pools[i].sp_nrthrmax);
> >  	return max;
> >  }
> > diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
> > index 63d1002e63e7..40040af588fb 100644
> > --- a/net/sunrpc/svc_xprt.c
> > +++ b/net/sunrpc/svc_xprt.c
> > @@ -1188,7 +1188,7 @@ static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net)
> >  	struct svc_xprt *xprt;
> >  	int i;
> >  
> > -	for (i = 0; i < serv->sv_nrpools; i++) {
> > +	for (i = 0; i < svc_serv_nrpools(serv); i++) {
> >  		struct svc_pool *pool = &serv->sv_pools[i];
> >  		struct llist_node *q, **t1, *t2;
> >  
> > @@ -1517,7 +1517,7 @@ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
> >  		return SEQ_START_TOKEN;
> >  	if (!si->serv)
> >  		return NULL;
> > -	return pidx > si->serv->sv_nrpools ? NULL
> > +	return pidx > svc_serv_nrpools(si->serv) ? NULL
> >  		: &si->serv->sv_pools[pidx - 1];
> >  }
> >  
> > @@ -1535,7 +1535,7 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
> >  		pool = &serv->sv_pools[0];
> >  	} else {
> >  		unsigned int pidx = (pool - &serv->sv_pools[0]);
> > -		if (pidx < serv->sv_nrpools-1)
> > +		if (pidx < svc_serv_nrpools(serv) - 1)
> >  			pool = &serv->sv_pools[pidx+1];
> >  		else
> >  			pool = NULL;
> > 
> > -- 
> > 2.55.0
> > 
> > 

-- 
Jeff Layton <[email protected]>