Re: [PATCH v5 02/11] x86,fs/resctrl: Document safe RCU list traversal

[Ben Horgan]

Hi Reinette,

On 6/9/26 22:02, Reinette Chatre wrote:
> rdt_resource::ctrl_domains and rdt_resource::mon_domains are RCU lists with
> entries added and removed by architecture from CPU hotplug callbacks that
> are run with cpus_write_lock() held. These lists can be traversed safely
> from resctrl fs by either holding cpus_read_lock() or relying on an RCU
> read-side critical section.
> 
> resctrl fs traversals of rdt_resource::ctrl_domains and
> rdt_resource::mon_domains are done using list_for_each_entry() with
> cpus_read_lock() held. Similarly, x86 architecture callbacks use
> list_for_each_entry() expecting that resctrl fs makes the call with
> cpus_read_lock() held. Inconsistently, a lockdep_assert_cpus_held() precedes
> the list_for_each_entry() call with varying distance to document this safe
> RCU list traversal.
> 
> In preparation for an upcoming traversal of rdt_resource::ctrl_domains that
> needs to be done from RCU read-side critical section there is a requirement
> for developers to always know exactly in which context the list is being
> traversed.
> 
> Replace the list_for_each_entry() traversals of RCU list with
> list_for_each_entry_rcu() to document that an RCU list is being traversed
> while making use of the built-in lockdep expression that additionally
> documents that it is cpus_read_lock() that enables the list to be
> traversed from non-RCU protection. Only revert to documenting the
> safety of traversal using a comment when lockdep does not have needed
> visibility in functions called via smp_call*().
> 
> The lockdep expression within list_for_each_entry_rcu() depends on
> RCU_EXPERT that is not set in a typical debug kernel so keep the existing
> lockdep_assert_cpus_held() that is active with CONFIG_LOCKDEP=y found in
> typical debug kernel.
> 
> Signed-off-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>

Seems good to me. I can add the same for the MPAM driver.

Thanks,

Ben

> ---
> Changes since v3:
> - New patch.
> ---
>  arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  4 ++--
>  arch/x86/kernel/cpu/resctrl/monitor.c     |  2 +-
>  arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  4 ++--
>  fs/resctrl/ctrlmondata.c                  | 12 +++++++-----
>  fs/resctrl/monitor.c                      | 23 +++++++++++++---------
>  fs/resctrl/pseudo_lock.c                  |  2 +-
>  fs/resctrl/rdtgroup.c                     | 24 +++++++++++------------
>  7 files changed, 39 insertions(+), 32 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> index b20e705606b8..e74f1ed54b86 100644
> --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> @@ -53,7 +53,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
>  	/* Walking r->domains, ensure it can't race with cpuhp */
>  	lockdep_assert_cpus_held();
>  
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		hw_dom = resctrl_to_arch_ctrl_dom(d);
>  		msr_param.res = NULL;
>  		for (t = 0; t < CDP_NUM_TYPES; t++) {
> @@ -115,7 +115,7 @@ static void _resctrl_sdciae_enable(struct rdt_resource *r, bool enable)
>  	lockdep_assert_cpus_held();
>  
>  	/* Update MSR_IA32_L3_QOS_EXT_CFG MSR on all the CPUs in all domains */
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list)
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held())
>  		on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_sdciae_set_one_amd, &enable, 1);
>  }
>  
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 569894d6e5c8..430b8fae0b77 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -510,7 +510,7 @@ static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable)
>  
>  	lockdep_assert_cpus_held();
>  
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_abmc_set_one_amd,
>  				 &enable, 1);
>  		resctrl_arch_reset_rmid_all(r, d);
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 885026468440..5ffa39fa86fa 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -151,7 +151,7 @@ static int set_cache_qos_cfg(int level, bool enable)
>  		return -ENOMEM;
>  
>  	r_l = &rdt_resources_all[level].r_resctrl;
> -	list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r_l->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (r_l->cache.arch_has_per_cpu_cfg)
>  			/* Pick all the CPUs in the domain instance */
>  			for_each_cpu(cpu, &d->hdr.cpu_mask)
> @@ -249,7 +249,7 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
>  	 * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU
>  	 * from each domain to update the MSRs below.
>  	 */
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		hw_dom = resctrl_to_arch_ctrl_dom(d);
>  
>  		for (i = 0; i < hw_res->num_closid; i++)
> diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
> index 9a7dfc48cb2e..f33712c17d38 100644
> --- a/fs/resctrl/ctrlmondata.c
> +++ b/fs/resctrl/ctrlmondata.c
> @@ -261,7 +261,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
>  		return -EINVAL;
>  	}
>  	dom = strim(dom);
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (d->hdr.id == dom_id) {
>  			data.buf = dom;
>  			data.closid = rdtgrp->closid;
> @@ -397,7 +397,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema,
>  
>  	if (resource_name)
>  		seq_printf(s, "%*s:", max_name_width, resource_name);
> -	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(dom, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (sep)
>  			seq_puts(s, ";");
>  
> @@ -535,6 +535,8 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
>  	struct rdt_domain_hdr *d;
>  	struct list_head *l;
>  
> +	lockdep_assert_cpus_held();
> +
>  	list_for_each(l, h) {
>  		d = list_entry(l, struct rdt_domain_hdr, list);
>  		/* When id is found, return its domain. */
> @@ -717,7 +719,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
>  		 * struct mon_data. Search all domains in the resource for
>  		 * one that matches this cache id.
>  		 */
> -		list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  			if (d->ci_id == domid) {
>  				cpu = cpumask_any(&d->hdr.cpu_mask);
>  				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
> @@ -817,7 +819,7 @@ static int resctrl_io_alloc_init_cbm(struct resctrl_schema *s, u32 closid)
>  	/* Keep CDP_CODE and CDP_DATA of io_alloc CLOSID's CBM in sync. */
>  	if (resctrl_arch_get_cdp_enabled(r->rid)) {
>  		peer_type = resctrl_peer_type(s->conf_type);
> -		list_for_each_entry(d, &s->res->ctrl_domains, hdr.list)
> +		list_for_each_entry_rcu(d, &s->res->ctrl_domains, hdr.list, lockdep_is_cpus_held())
>  			memcpy(&d->staged_config[peer_type],
>  			       &d->staged_config[s->conf_type],
>  			       sizeof(d->staged_config[0]));
> @@ -980,7 +982,7 @@ static int resctrl_io_alloc_parse_line(char *line,  struct rdt_resource *r,
>  	}
>  
>  	dom = strim(dom);
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (update_all || d->hdr.id == dom_id) {
>  			data.buf = dom;
>  			data.mode = RDT_MODE_SHAREABLE;
> diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
> index a932a1fea818..2dacb589625d 100644
> --- a/fs/resctrl/monitor.c
> +++ b/fs/resctrl/monitor.c
> @@ -309,7 +309,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>  	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
>  
>  	entry->busy = 0;
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		/*
>  		 * For the first limbo RMID in the domain,
>  		 * setup up the limbo worker.
> @@ -507,6 +507,11 @@ static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *r
>  	 * all domains fail for any reason.
>  	 */
>  	ret = -EINVAL;
> +	/*
> +	 * RCU list being traversed with CPU hotplug lock held. lockdep
> +	 * unable to help prove this here since this work is scheduled via
> +	 * smp_call*(). Not called from MBM overflow handler.
> +	 */
>  	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
>  		if (d->ci_id != rr->ci->id)
>  			continue;
> @@ -1231,7 +1236,7 @@ static int rdtgroup_assign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgro
>  	int ret = 0;
>  
>  	if (!d) {
> -		list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  			int err;
>  
>  			err = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
> @@ -1303,7 +1308,7 @@ static void rdtgroup_unassign_cntr_event(struct rdt_l3_mon_domain *d, struct rdt
>  	struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid);
>  
>  	if (!d) {
> -		list_for_each_entry(d, &r->mon_domains, hdr.list)
> +		list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held())
>  			rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt);
>  	} else {
>  		rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt);
> @@ -1375,7 +1380,7 @@ static void rdtgroup_update_cntr_event(struct rdt_resource *r, struct rdtgroup *
>  	struct rdt_l3_mon_domain *d;
>  	int cntr_id;
>  
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		cntr_id = mbm_cntr_get(r, d, rdtgrp, evtid);
>  		if (cntr_id >= 0)
>  			rdtgroup_assign_cntr(r, d, evtid, rdtgrp->mon.rmid,
> @@ -1545,7 +1550,7 @@ ssize_t resctrl_mbm_assign_mode_write(struct kernfs_open_file *of, char *buf,
>  		/*
>  		 * Reset all the non-achitectural RMID state and assignable counters.
>  		 */
> -		list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  			mbm_cntr_free_all(r, d);
>  			resctrl_reset_rmid_all(r, d);
>  		}
> @@ -1568,7 +1573,7 @@ int resctrl_num_mbm_cntrs_show(struct kernfs_open_file *of,
>  	cpus_read_lock();
>  	mutex_lock(&rdtgroup_mutex);
>  
> -	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(dom, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (sep)
>  			seq_putc(s, ';');
>  
> @@ -1602,7 +1607,7 @@ int resctrl_available_mbm_cntrs_show(struct kernfs_open_file *of,
>  		goto out_unlock;
>  	}
>  
> -	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(dom, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (sep)
>  			seq_putc(s, ';');
>  
> @@ -1652,7 +1657,7 @@ int mbm_L3_assignments_show(struct kernfs_open_file *of, struct seq_file *s, voi
>  
>  		sep = false;
>  		seq_printf(s, "%s:", mevt->name);
> -		list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  			if (sep)
>  				seq_putc(s, ';');
>  
> @@ -1750,7 +1755,7 @@ static int resctrl_parse_mbm_assignment(struct rdt_resource *r, struct rdtgroup
>  	}
>  
>  	/* Verify if the dom_id is valid */
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (d->hdr.id == dom_id) {
>  			ret = rdtgroup_modify_assign_state(dom_str, d, rdtgrp, mevt);
>  			if (ret) {
> diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
> index d1cb0986006e..dea2b4bf966f 100644
> --- a/fs/resctrl/pseudo_lock.c
> +++ b/fs/resctrl/pseudo_lock.c
> @@ -656,7 +656,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
>  	 * associated with them.
>  	 */
>  	for_each_alloc_capable_rdt_resource(r) {
> -		list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
> +		list_for_each_entry_rcu(d_i, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  			if (d_i->plr)
>  				cpumask_or(cpu_with_psl, cpu_with_psl,
>  					   &d_i->hdr.cpu_mask);
> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
> index af2cbab14497..2a6221925767 100644
> --- a/fs/resctrl/rdtgroup.c
> +++ b/fs/resctrl/rdtgroup.c
> @@ -117,7 +117,7 @@ void rdt_staged_configs_clear(void)
>  	lockdep_assert_held(&rdtgroup_mutex);
>  
>  	for_each_alloc_capable_rdt_resource(r) {
> -		list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
> +		list_for_each_entry_rcu(dom, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held())
>  			memset(dom->staged_config, 0, sizeof(dom->staged_config));
>  	}
>  }
> @@ -1063,7 +1063,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
>  
>  	cpus_read_lock();
>  	mutex_lock(&rdtgroup_mutex);
> -	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(dom, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (sep)
>  			seq_putc(seq, ';');
>  		hw_shareable = r->cache.shareable_bits;
> @@ -1415,7 +1415,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
>  		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
>  			continue;
>  		has_cache = true;
> -		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  			ctrl = resctrl_arch_get_config(r, d, closid,
>  						       s->conf_type);
>  			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
> @@ -1604,7 +1604,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
>  		type = schema->conf_type;
>  		sep = false;
>  		seq_printf(s, "%*s:", max_name_width, schema->name);
> -		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +		list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  			if (sep)
>  				seq_putc(s, ';');
>  			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
> @@ -1649,7 +1649,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
>  	cpus_read_lock();
>  	mutex_lock(&rdtgroup_mutex);
>  
> -	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(dom, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (sep)
>  			seq_puts(s, ";");
>  
> @@ -1763,7 +1763,7 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
>  		return -EINVAL;
>  	}
>  
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (d->hdr.id == dom_id) {
>  			mbm_config_write_domain(r, d, evtid, val);
>  			goto next;
> @@ -2554,7 +2554,7 @@ static int set_mba_sc(bool mba_sc)
>  
>  	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
>  
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		for (i = 0; i < num_closid; i++)
>  			d->mbps_val[i] = MBA_MAX_MBPS;
>  	}
> @@ -2879,7 +2879,7 @@ static int rdt_get_tree(struct fs_context *fc)
>  
>  	if (resctrl_is_mbm_enabled()) {
>  		r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
> -		list_for_each_entry(dom, &r->mon_domains, hdr.list)
> +		list_for_each_entry_rcu(dom, &r->mon_domains, hdr.list, lockdep_is_cpus_held())
>  			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
>  						   RESCTRL_PICK_ANY_CPU);
>  	}
> @@ -3435,7 +3435,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
>  	/* Walking r->domains, ensure it can't race with cpuhp */
>  	lockdep_assert_cpus_held();
>  
> -	list_for_each_entry(hdr, &r->mon_domains, list) {
> +	list_for_each_entry_rcu(hdr, &r->mon_domains, list, lockdep_is_cpus_held()) {
>  		ret = mkdir_mondata_subdir(parent_kn, hdr, r, prgrp);
>  		if (ret)
>  			return ret;
> @@ -3620,7 +3620,7 @@ int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
>  	struct rdt_ctrl_domain *d;
>  	int ret;
>  
> -	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &s->res->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		ret = __init_one_rdt_domain(d, s, closid);
>  		if (ret < 0)
>  			return ret;
> @@ -3635,7 +3635,7 @@ static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
>  	struct resctrl_staged_config *cfg;
>  	struct rdt_ctrl_domain *d;
>  
> -	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->ctrl_domains, hdr.list, lockdep_is_cpus_held()) {
>  		if (is_mba_sc(r)) {
>  			d->mbps_val[closid] = MBA_MAX_MBPS;
>  			continue;
> @@ -4506,7 +4506,7 @@ static struct rdt_l3_mon_domain *get_mon_domain_from_cpu(int cpu,
>  
>  	lockdep_assert_cpus_held();
>  
> -	list_for_each_entry(d, &r->mon_domains, hdr.list) {
> +	list_for_each_entry_rcu(d, &r->mon_domains, hdr.list, lockdep_is_cpus_held()) {
>  		/* Find the domain that contains this CPU */
>  		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
>  			return d;