x86/resctrl: Abstract __rmid_read()

__rmid_read() selects the specified eventid and returns the counter
value from the MSR. The error handling is architecture specific, and
handled by the callers, rdtgroup_mondata_show() and __mon_event_count().

Error handling should be handled by architecture specific code, as
a different architecture may have different requirements. MPAM's
counters can report that they are 'not ready', requiring a second
read after a short delay. This should be hidden from resctrl.

Make __rmid_read() the architecture specific function for reading
a counter. Rename it resctrl_arch_rmid_read() and move the error
handling into it.

A read from a counter that hardware supports but resctrl does not
now returns -EINVAL instead of -EIO from the default case in
__mon_event_count(). It isn't possible for user-space to see this
change as resctrl doesn't expose counters it doesn't support.

Signed-off-by: James Morse <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Jamie Iles <[email protected]>
Reviewed-by: Shaopeng Tan <[email protected]>
Reviewed-by: Reinette Chatre <[email protected]>
Tested-by: Xin Hao <[email protected]>
Tested-by: Shaopeng Tan <[email protected]>
Tested-by: Cristian Marussi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: James Morse

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -579,9 +579,9 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
-	if (rr.val & RMID_VAL_ERROR)
+	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");
-	else if (rr.val & RMID_VAL_UNAVAIL)
+	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
 	else
 		seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);

arch/x86/kernel/cpu/resctrl/internal.h

@@ -94,6 +94,7 @@ struct rmid_read {
 	struct rdt_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
+	int			err;
 	u64			val;
 };
 

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -167,9 +167,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 		memset(am, 0, sizeof(*am));
 }
 
-static u64 __rmid_read(u32 rmid, enum resctrl_event_id eventid)
+int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
-	u64 val;
+	u64 msr_val;
 
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
@@ -180,14 +180,24 @@ static u64 __rmid_read(u32 rmid, enum resctrl_event_id eventid)
 	 * are error bits.
 	 */
 	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, val);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
-	return val;
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+
+	return 0;
 }
 
 static bool rmid_dirty(struct rmid_entry *entry)
 {
-	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+	u64 val = 0;
+
+	if (resctrl_arch_rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val))
+		return true;
 
 	return val >= resctrl_cqm_threshold;
 }
@@ -259,17 +269,19 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r;
 	struct rdt_domain *d;
-	int cpu;
-	u64 val;
+	int cpu, err;
+	u64 val = 0;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
 	entry->busy = 0;
 	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
-			if (val <= resctrl_cqm_threshold)
+			err = resctrl_arch_rmid_read(entry->rmid,
+						     QOS_L3_OCCUP_EVENT_ID,
+						     &val);
+			if (err || val <= resctrl_cqm_threshold)
 				continue;
 		}
 
@@ -315,19 +327,19 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m;
-	u64 chunks, tval;
+	u64 chunks, tval = 0;
 
 	if (rr->first)
 		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
 
-	tval = __rmid_read(rmid, rr->evtid);
-	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
-		return tval;
-	}
+	rr->err = resctrl_arch_rmid_read(rmid, rr->evtid, &tval);
+	if (rr->err)
+		return rr->err;
+
 	switch (rr->evtid) {
 	case QOS_L3_OCCUP_EVENT_ID:
 		rr->val += tval;
@@ -341,9 +353,9 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 	default:
 		/*
 		 * Code would never reach here because an invalid
-		 * event id would fail the __rmid_read.
+		 * event id would fail in resctrl_arch_rmid_read().
 		 */
-		return RMID_VAL_ERROR;
+		return -EINVAL;
 	}
 
 	if (rr->first) {
@@ -399,11 +411,11 @@ void mon_event_count(void *info)
 	struct rdtgroup *rdtgrp, *entry;
 	struct rmid_read *rr = info;
 	struct list_head *head;
-	u64 ret_val;
+	int ret;
 
 	rdtgrp = rr->rgrp;
 
-	ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp->mon.rmid, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -415,13 +427,17 @@ void mon_event_count(void *info)
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
 			if (__mon_event_count(entry->mon.rmid, rr) == 0)
-				ret_val = 0;
+				ret = 0;
 		}
 	}
 
-	/* Report error if none of rmid_reads are successful */
-	if (ret_val)
-		rr->val = ret_val;
+	/*
+	 * __mon_event_count() calls for newly created monitor groups may
+	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
+	 * Discard error if any of the monitor event reads succeeded.
+	 */
+	if (ret == 0)
+		rr->err = 0;
 }
 
 /*

include/linux/resctrl.h

@@ -219,6 +219,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
+int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *res);
 
 /**
  * resctrl_arch_reset_rmid() - Reset any private state associated with rmid