fs/resctrl: Support counter read/reset with mbm_event assignment mode

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 an event without assigning a hardware counter.

Suggested-by: Reinette Chatre <[e-mail]>
Signed-off-by: Babu Moger <[e-mail]>
Signed-off-by: Borislav Petkov (AMD) <[e-mail]>
Reviewed-by: Reinette Chatre <[e-mail]>
Link: https://lore.kernel.org/[e-mail]

Documentation/filesystems/resctrl.rst

···
 	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.

fs/resctrl/ctrlmondata.c

···
 	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);
···
 	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)
···
 
 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);
 

fs/resctrl/internal.h

···
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
  * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it
+ *	   is an MBM event.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
···
 	enum resctrl_event_id	evtid;
 	bool			first;
 	struct cacheinfo	*ci;
+	bool			is_mbm_cntr;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;

fs/resctrl/monitor.c

···
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
 	struct rdt_mon_domain *d;
+	int cntr_id = -ENOENT;
 	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));
···
 		/* 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;
 
···
 	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;
···
 	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)) {
+		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);
···
 	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,