Re: [PATCH v16 23/34] fs/resctrl: Support counter read/reset with mbm_event assignment mode

["Moger, Babu" <babu.moger@amd.com>]

Hi Reinette,

On 7/30/25 15:03, Reinette Chatre wrote:
> Hi Babu,
> 
> On 7/25/25 11:29 AM, Babu Moger wrote:
>> When "mbm_event" counter assignment mode is enabled, the architecture
>> requires a counter ID to read the event data.
>>
>> Introduce an is_mbm_cntr field in struct rmid_read to indicate whether
>> counter assignment mode is in use.
>>
>> Update the logic to call resctrl_arch_cntr_read() and
>> resctrl_arch_reset_cntr() when the assignment mode is active. Report
>> 'Unassigned' in case the user attempts to read the event without assigning
>> a hardware counter.
>>
>> Declare mbm_cntr_get() in fs/resctrl/internal.h to make it accessible to
>> other functions within fs/resctrl.
> 
>>From what I can tell this is not needed by this patch. It is also a hint that
> there may be some monitoring specific code outside of monitor.c. Looks like this
> is done to support later patch #29 "fs/resctrl: Introduce mbm_L3_assignments to
> list assignments in a group" where mbm_L3_assignments_show() should rather
> be in monitor.c

Yes. Will move all these to monitor.c.

> 
>>
>> Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
>> Signed-off-by: Babu Moger <babu.moger@amd.com>
>> ---
> ...
> 
>> ---
>>  Documentation/filesystems/resctrl.rst |  6 ++++
>>  fs/resctrl/ctrlmondata.c              | 22 +++++++++---
>>  fs/resctrl/internal.h                 |  5 +++
>>  fs/resctrl/monitor.c                  | 52 ++++++++++++++++++++-------
>>  4 files changed, 67 insertions(+), 18 deletions(-)
>>
>> diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
>> index 446736dbd97f..4c24c5f3f4c1 100644
>> --- a/Documentation/filesystems/resctrl.rst
>> +++ b/Documentation/filesystems/resctrl.rst
>> @@ -434,6 +434,12 @@ When monitoring is enabled all MON groups will also contain:
>>  	for the L3 cache they occupy). These are named "mon_sub_L3_YY"
>>  	where "YY" is the node number.
>>  
>> +	When the 'mbm_event' counter assignment mode is enabled, reading
>> +	an MBM event of a MON group returns 'Unassigned' if no hardware
>> +	counter is assigned to it. For CTRL_MON groups, 'Unassigned' is
>> +	returned if the MBM event does not have an assigned counter in the
>> +	CTRL_MON group nor in any of its associated MON groups.
>> +
>>  "mon_hw_id":
>>  	Available only with debug option. The identifier used by hardware
>>  	for the monitor group. On x86 this is the RMID.
>> diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
>> index ad7ffc6acf13..31787ce6ec91 100644
>> --- a/fs/resctrl/ctrlmondata.c
>> +++ b/fs/resctrl/ctrlmondata.c
>> @@ -563,10 +563,15 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
>>  	rr->r = r;
>>  	rr->d = d;
>>  	rr->first = first;
>> -	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
>> -	if (IS_ERR(rr->arch_mon_ctx)) {
>> -		rr->err = -EINVAL;
>> -		return;
>> +	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
>> +	    resctrl_is_mbm_event(evtid)) {
>> +		rr->is_mbm_cntr = true;
>> +	} else {
>> +		rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
>> +		if (IS_ERR(rr->arch_mon_ctx)) {
>> +			rr->err = -EINVAL;
>> +			return;
>> +		}
>>  	}
>>  
>>  	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
>> @@ -582,7 +587,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
>>  	else
>>  		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
>>  
>> -	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
>> +	if (rr->arch_mon_ctx)
>> +		resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
>>  }
>>  
>>  int rdtgroup_mondata_show(struct seq_file *m, void *arg)
>> @@ -653,10 +659,16 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
>>  
>>  checkresult:
>>  
>> +	/*
>> +	 * -ENOENT is a special case, set only when "mbm_event" counter assignment
>> +	 * mode is enabled and no counter has been assigned.
>> +	 */
>>  	if (rr.err == -EIO)
>>  		seq_puts(m, "Error\n");
>>  	else if (rr.err == -EINVAL)
>>  		seq_puts(m, "Unavailable\n");
>> +	else if (rr.err == -ENOENT)
>> +		seq_puts(m, "Unassigned\n");
>>  	else
>>  		seq_printf(m, "%llu\n", rr.val);
>>  
>> diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
>> index 216588842444..eeee83a5067a 100644
>> --- a/fs/resctrl/internal.h
>> +++ b/fs/resctrl/internal.h
>> @@ -110,6 +110,8 @@ struct mon_data {
>>   *	   domains in @r sharing L3 @ci.id
>>   * @evtid: Which monitor event to read.
>>   * @first: Initialize MBM counter when true.
>> + * @is_mbm_cntr: Is the counter valid? true if "mbm_event" counter assignment mode is
>> + *	   enabled and it is an MBM event.
> 
> Since a counter may not be assigned to event being read I do not believe that "Is the counter
> valid?" is accurate and should rather be dropped. Rest of text looks accurate to me.  

Sure.

> 
>>   * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
>>   * @err:   Error encountered when reading counter.
>>   * @val:   Returned value of event counter. If @rgrp is a parent resource group,
>> @@ -124,6 +126,7 @@ struct rmid_read {
>>  	struct rdt_mon_domain	*d;
>>  	enum resctrl_event_id	evtid;
>>  	bool			first;
>> +	bool			is_mbm_cntr;
>>  	unsigned int		ci_id;
>>  	int			err;
>>  	u64			val;
>> @@ -391,6 +394,8 @@ int rdtgroup_assign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp
>>  			       struct mon_evt *mevt);
>>  void rdtgroup_unassign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
>>  				  struct mon_evt *mevt);
>> +int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
>> +		 struct rdtgroup *rdtgrp, enum resctrl_event_id evtid);
>>  
> 
> Not necessary? mbm_cntr_get() can remain internal to monitor.c

Yes. Not necessary.

> 
>>  #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
>>  int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
>> diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
>> index 070965d45770..a8b53b0ad0b7 100644
>> --- a/fs/resctrl/monitor.c
>> +++ b/fs/resctrl/monitor.c
>> @@ -362,13 +362,25 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
>>  	u32 closid = rdtgrp->closid;
>>  	u32 rmid = rdtgrp->mon.rmid;
>>  	struct rdt_mon_domain *d;
>> +	int cntr_id = -ENOENT;
>>  	struct cacheinfo *ci;
>>  	struct mbm_state *m;
>>  	int err, ret;
>>  	u64 tval = 0;
>>  
>> +	if (rr->is_mbm_cntr) {
>> +		cntr_id = mbm_cntr_get(rr->r, rr->d, rdtgrp, rr->evtid);
>> +		if (cntr_id < 0) {
>> +			rr->err = -ENOENT;
>> +			return -EINVAL;
>> +		}
>> +	}
>> +
>>  	if (rr->first) {
>> -		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
>> +		if (rr->is_mbm_cntr)
>> +			resctrl_arch_reset_cntr(rr->r, rr->d, closid, rmid, cntr_id, rr->evtid);
>> +		else
>> +			resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
>>  		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
>>  		if (m)
>>  			memset(m, 0, sizeof(struct mbm_state));
>> @@ -379,8 +391,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
>>  		/* Reading a single domain, must be on a CPU in that domain. */
>>  		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
>>  			return -EINVAL;
>> -		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
>> -						 rr->evtid, &tval, rr->arch_mon_ctx);
>> +		if (rr->is_mbm_cntr)
>> +			rr->err = resctrl_arch_cntr_read(rr->r, rr->d, closid, rmid, cntr_id,
>> +							 rr->evtid, &tval);
>> +		else
>> +			rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
>> +							 rr->evtid, &tval, rr->arch_mon_ctx);
>>  		if (rr->err)
>>  			return rr->err;
>>  
>> @@ -405,8 +421,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
>>  	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
>>  		if (d->ci_id != rr->ci_id)
>>  			continue;
>> -		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
>> -					     rr->evtid, &tval, rr->arch_mon_ctx);
>> +		if (rr->is_mbm_cntr)
>> +			err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
>> +						     rr->evtid, &tval);
>> +		else
>> +			err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
>> +						     rr->evtid, &tval, rr->arch_mon_ctx);
>>  		if (!err) {
>>  			rr->val += tval;
>>  			ret = 0;
>> @@ -613,11 +633,16 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
>>  	rr.r = r;
>>  	rr.d = d;
>>  	rr.evtid = evtid;
>> -	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
>> -	if (IS_ERR(rr.arch_mon_ctx)) {
>> -		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
>> -				    PTR_ERR(rr.arch_mon_ctx));
>> -		return;
>> +	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
>> +	    resctrl_arch_mbm_cntr_assign_enabled(r)) {
> 
> Duplicate check?

Yes.

> 
>> +		rr.is_mbm_cntr = true;
>> +	} else {
>> +		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
>> +		if (IS_ERR(rr.arch_mon_ctx)) {
>> +			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
>> +					    PTR_ERR(rr.arch_mon_ctx));
>> +			return;
>> +		}
>>  	}
>>  
>>  	__mon_event_count(rdtgrp, &rr);
>> @@ -629,7 +654,8 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
>>  	if (is_mba_sc(NULL))
>>  		mbm_bw_count(rdtgrp, &rr);
>>  
>> -	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
>> +	if (rr.arch_mon_ctx)
>> +		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
>>  }
>>  
>>  static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
>> @@ -983,8 +1009,8 @@ static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *
>>   * Return:
>>   * Valid counter ID on success, or -ENOENT on failure.
>>   */
>> -static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
>> -			struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
>> +int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
>> +		 struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
>>  {
>>  	int cntr_id;
>>  
> 
> Not necessary?
> 

Yes.

-- 
Thanks
Babu Moger